© 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. 30997
    Prev
    Next
    INDEX
    Explanations

    specific tokens followed by other tokens

    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
     isComment
    -0.80
     Já
    -0.75
     europ
    -0.75
     vehicles
    -0.74
    スタイ
    -0.73
     seria
    -0.71
     обна
    -0.71
     sõ
    -0.70
     automobiles
    -0.70
     Buna
    -0.69
    POSITIVE LOGITS
     vuelve
    0.77
     Unit
    0.76
     jednost
    0.75
    Unit
    0.75
    遭
    0.74
     External
    0.73
    VU
    0.73
    FAILURE
    0.72
    aree
    0.72
    بران
    0.72
    Activations Density 0.016%

    No Known Activations