© 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. 117649
    Prev
    Next
    INDEX
    Explanations

    Subject, video, downloads

    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
    iempo
    -0.71
    ckpt
    -0.67
    zyst
    -0.67
     commenting
    -0.66
    alige
    -0.65
    kiewicz
    -0.65
    新的
    -0.64
     nông
    -0.63
    GRP
    -0.63
    rasco
    -0.63
    POSITIVE LOGITS
    acne
    0.80
    /'+
    0.69
     veci
    0.69
     unfor
    0.69
    Removal
    0.68
     Mistake
    0.68
     내
    0.68
     acne
    0.68
    Syd
    0.68
    maxi
    0.67
    Activations Density 0.066%

    No Known Activations