© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7376
    Prev
    Next
    INDEX
    Explanations

    changes and cancellations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects references to formal legal or governmental actions—terms signaling laws, regulations, or official policy changes (e.g. enacted, law, act, amended, rescinded).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    clauses describing legal, regulatory, or policy changes and their implementation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of laws, regulations, and government policies, especially their enactment, modification, rescission, enforcement, or compliance requirements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impactful
    1.31
     underwhelming
    1.09
     देखील
    1.02
    utilizzo
    1.02
     skillset
    1.00
     photoshoot
    0.97
     العديد
    0.96
    ⛰
    0.94
     sosok
    0.93
     المُ
    0.92
    POSITIVE LOGITS
    
    0.96
     nonuniform
    0.79
     hassles
    0.77
     பிரச்
    0.76
     healthful
    0.75
     enforcement
    0.75
     uniformity
    0.75
     violators
    0.74
    -
    0.74
    規定
    0.74
    Activations Density 0.063%

    No Known Activations