© 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. 127675
    Prev
    Next
    INDEX
    Explanations

    foreign language or code identifiers

    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
    faden
    -0.84
    ští
    -0.82
     until
    -0.79
    It
    -0.79
    ać
    -0.73
    Until
    -0.73
     Until
    -0.72
    𝗣
    -0.71
     объяс
    -0.70
    قرير
    -0.70
    POSITIVE LOGITS
     gentes
    0.91
    elesen
    0.91
    Kapcsolódó
    0.87
     maisha
    0.85
     staden
    0.84
    REQUIRES
    0.82
    ौर
    0.79
    τρο
    0.79
     offent
    0.79
     trasladado
    0.79
    Activations Density 0.032%

    No Known Activations