© 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. 62760
    Prev
    Next
    INDEX
    Explanations

    code copyright license

    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
    jetunion
    -0.88
    Boxes
    -0.76
     advantages
    -0.75
     naselje
    -0.75
    cedent
    -0.74
     frühen
    -0.74
     显
    -0.74
     Etapa
    -0.73
    超過
    -0.72
    ciata
    -0.72
    POSITIVE LOGITS
    USC
    0.72
    ב
    0.71
     годи
    0.69
     Olds
    0.69
     divest
    0.69
    _-
    0.68
     colonized
    0.68
     reinforcing
    0.66
    Notre
    0.66
    𝘪
    0.66
    Activations Density 0.022%

    No Known Activations