© 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. 106437
    Prev
    Next
    INDEX
    Explanations

    subject class classification keywords

    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
    ieš
    -0.84
    dialement
    -0.74
    ❆
    -0.74
    服用
    -0.74
     differentiate
    -0.73
     Europeans
    -0.72
    外交
    -0.71
     veroor
    -0.71
    adell
    -0.71
    िला
    -0.70
    POSITIVE LOGITS
    Keywords
    1.15
     keywords
    1.09
    PACS
    1.09
     Keywords
    1.02
     miscellaneous
    1.00
    general
    0.96
     general
    0.95
     keyword
    0.94
    Misc
    0.94
    cellaneous
    0.92
    Activations Density 0.019%

    No Known Activations