© 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. 29894
    Prev
    Next
    INDEX
    Explanations

    font face color

    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
     privados
    -0.76
     begann
    -0.74
     Further
    -0.73
     dites
    -0.71
     основу
    -0.71
     Full
    -0.71
     Säure
    -0.71
    頭
    -0.70
     продукта
    -0.69
    對
    -0.69
    POSITIVE LOGITS
     color
    1.55
     face
    1.34
     COLOR
    1.20
     colour
    1.18
    color
    1.13
    Color
    1.11
    FACE
    1.09
    setColor
    1.09
    face
    1.05
    COLOR
    1.05
    Activations Density 0.017%

    No Known Activations