© 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. 30014
    Prev
    Next
    INDEX
    Explanations

    UI menus and code files

    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
    Negative Logits
     during
    -0.84
     verksamhet
    -0.75
     now
    -0.75
     Sundance
    -0.74
     上
    -0.72
    leine
    -0.71
     Dostupné
    -0.71
     ilmiah
    -0.70
    ের
    -0.70
    中に
    -0.70
    POSITIVE LOGITS
    noons
    0.84
    原料
    0.83
    @
    0.82
    acheter
    0.80
    Quantitative
    0.80
    Temas
    0.80
    Ри
    0.79
     कु
    0.79
    Material
    0.79
    ถาม
    0.79
    Activations Density 0.001%

    No Known Activations