© 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. 106464
    Prev
    Next
    INDEX
    Explanations

    code must

    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
    czenia
    -0.84
     naast
    -0.80
    从小
    -0.78
    pley
    -0.76
    lenül
    -0.76
    grunns
    -0.75
     Coolidge
    -0.74
    诲
    -0.74
     fuss
    -0.73
     الكه
    -0.73
    POSITIVE LOGITS
     nuestro
    0.92
    ‡
    0.85
     özel
    0.82
     Emissions
    0.78
    Tensi
    0.77
     private
    0.77
    alu
    0.76
     AssertionError
    0.76
     heutigen
    0.76
    obrá
    0.76
    Activations Density 0.000%

    No Known Activations