© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90087
    Prev
    Next
    INDEX
    Explanations

    legal citations and disclaimers

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

    This neuron spotlights tokens that are part of legal-case citations (e.g. volume/page numbers and reporter abbreviations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createStore
    -0.77
    Contributing
    -0.68
     TCU
    -0.67
     gcd
    -0.67
    Miracle
    -0.65
     projectile
    -0.65
     Koy
    -0.65
    Kram
    -0.63
     corrected
    -0.63
     المحت
    -0.63
    POSITIVE LOGITS
     RelativeLayout
    0.71
     uzyska
    0.69
     cards
    0.67
    вода
    0.67
     зо
    0.66
    formaz
    0.65
     guerr
    0.65
    Ḡ
    0.65
    かり
    0.65
    Might
    0.65
    Activations Density 0.101%

    No Known Activations