© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3355
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

    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
     uporab
    -0.77
     aconte
    -0.75
    ératures
    -0.74
     commandments
    -0.69
    Beng
    -0.69
    roses
    -0.69
    Dirs
    -0.68
    Gerard
    -0.68
     Seahawks
    -0.68
     tộc
    -0.68
    POSITIVE LOGITS
    getProducts
    0.86
    rodu
    0.82
     ")");
    0.79
    ABL
    0.77
    CD
    0.75
    VD
    0.75
    Blast
    0.74
    碎
    0.73
    compression
    0.73
     ApiClient
    0.72
    Activations Density 0.010%

    No Known Activations