© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103641
    Prev
    Next
    INDEX
    Explanations

    code and legal cases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     diferencial
    -0.83
    ounds
    -0.82
     Dama
    -0.80
    cota
    -0.79
     differentials
    -0.79
    自我
    -0.76
    peto
    -0.75
    挠
    -0.75
    unna
    -0.75
    YST
    -0.75
    POSITIVE LOGITS
    var
    1.11
     var
    0.98
     body
    0.93
     private
    0.75
     @
    0.72
     przys
    0.70
     let
    0.70
     soar
    0.69
     felony
    0.68
     including
    0.67
    Activations Density 0.012%

    No Known Activations