© 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. 30272
    Prev
    Next
    INDEX
    Explanations

    programming questions and code examples

    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
    立った
    -0.82
    Bras
    -0.77
    mitt
    -0.69
    Lz
    -0.68
     Melissa
    -0.68
     Policies
    -0.67
    ▐
    -0.66
    Entrée
    -0.66
    PROCED
    -0.65
     sogno
    -0.65
    POSITIVE LOGITS
     Llo
    0.96
    nemonic
    0.85
     BIP
    0.81
    aville
    0.79
     localVar
    0.77
    INV
    0.75
     loads
    0.74
    alo
    0.74
     INV
    0.74
    宽
    0.73
    Activations Density 0.009%

    No Known Activations