© 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. 78490
    Prev
    Next
    INDEX
    Explanations

    holy woman

    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
     Consequently
    -0.97
     esche
    -0.96
     Lastly
    -0.92
    idées
    -0.88
     currentUser
    -0.88
     selves
    -0.87
     Сайт
    -0.87
     Conversely
    -0.86
     タイプ
    -0.85
    encre
    -0.85
    POSITIVE LOGITS
     Emily
    0.73
     never
    0.71
    Emily
    0.70
    inerie
    0.69
    chak
    0.68
     nunca
    0.68
    {|
    0.68
    ビック
    0.68
     больше
    0.68
    ust
    0.68
    Activations Density 0.027%

    No Known Activations