© 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. 22-GEMMASCOPE-RES-131K
    7. 32588
    Prev
    Next
    INDEX
    Explanations

    information loading or description

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    wixt
    -0.98
    interesse
    -0.95
    testen
    -0.91
    Suara
    -0.91
    ligere
    -0.90
     while
    -0.88
    chowa
    -0.86
    lägen
    -0.85
    万年
    -0.85
     lutar
    -0.85
    POSITIVE LOGITS
     information
    0.89
    informationen
    0.88
     diſt
    0.87
     sheets
    0.87
     untersch
    0.86
    acij
    0.86
     description
    0.85
     AppBundle
    0.85
     जानकारी
    0.85
     gesammelt
    0.84
    Activations Density 0.049%

    No Known Activations