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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14487
    Prev
    Next
    INDEX
    Explanations

    requirements and regulations

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

    The neuron activates on language that lays out formal requirements or conditions—especially in legal, regulatory, or procedural contexts.

    oai_token-act-pair · o4-miniTriggered 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
    ต่างๆ
    0.77
     különböző
    0.77
     নানান
    0.73
     birçok
    0.71
     확대
    0.71
    いろんな
    0.70
     różnych
    0.69
    ዙ
    0.69
     разными
    0.68
    人们
    0.67
    POSITIVE LOGITS
    至少
    1.57
     almeno
    1.41
     mindestens
    1.41
     কমপক্ষে
    1.38
     verifiable
    1.30
     atleast
    1.28
     certify
    1.21
     demonstrable
    1.21
     demonstrate
    1.20
     минимум
    1.18
    Activations Density 1.387%

    No Known Activations