© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    according to

    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
     IH
    -0.92
     http
    -0.90
    WATCH
    -0.76
    chema
    -0.75
     inom
    -0.74
    ringer
    -0.73
    XS
    -0.73
    刺激
    -0.71
     AA
    -0.71
     Figures
    -0.69
    POSITIVE LOGITS
    私は
    0.79
     PROB
    0.76
    國家
    0.74
     ネックレス
    0.73
    ţin
    0.71
    還沒
    0.71
     Attraction
    0.70
    totalSupply
    0.70
     geloof
    0.70
     quarrel
    0.70
    Activations Density 0.007%

    No Known Activations