© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8262
    Prev
    Next
    INDEX
    Explanations

    grades or scores

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

    This neuron detects words commonly used in legal citations and formal legal references.

    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
    ｆ
    0.89
    ان
    0.86
    𝕤
    0.86
    ار
    0.80
    你有
    0.80
    鿓
    0.79
    älte
    0.78
    ко
    0.76
     inhom
    0.76
    د
    0.75
    POSITIVE LOGITS
     courageous
    0.83
     cherished
    0.80
     humana
    0.76
     martyrdom
    0.76
     minister
    0.73
     brave
    0.73
     captivity
    0.73
     (
    0.70
     world
    0.70
     kind
    0.69
    Activations Density 0.000%

    No Known Activations