© 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. 30238
    Prev
    Next
    INDEX
    Explanations

    AS IS clauses

    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
     Linked
    -0.82
    Linked
    -0.79
     Coach
    -0.73
    linked
    -0.69
     въ
    -0.69
    goku
    -0.69
    耦
    -0.68
    ‎
    -0.68
     LIM
    -0.68
    Nikita
    -0.68
    POSITIVE LOGITS
     Besoin
    0.76
     vontade
    0.71
     Frente
    0.69
     harap
    0.68
     għall
    0.68
    umbers
    0.68
    elyk
    0.66
     negozi
    0.65
     Worthy
    0.65
     Mentre
    0.65
    Activations Density 0.067%

    No Known Activations