© 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. 47420
    Prev
    Next
    INDEX
    Explanations

    find functions in code

    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
     corrida
    -0.73
     orel
    -0.71
     Chain
    -0.70
    AWARDS
    -0.70
    ister
    -0.69
     میدان
    -0.68
     prest
    -0.67
     Dif
    -0.66
     Shock
    -0.65
    rini
    -0.64
    POSITIVE LOGITS
    Johnson
    0.75
     tenang
    0.69
    gele
    0.68
    FRP
    0.67
    elu
    0.67
     jawaban
    0.64
    约翰
    0.63
    Ｂ
    0.63
     мәкал
    0.63
     Итали
    0.63
    Activations Density 0.048%

    No Known Activations