© 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. 10-GEMMASCOPE-RES-131K
    7. 71962
    Prev
    Next
    INDEX
    Explanations

    FC or band names with 'i' or 's' following

    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_10/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
     kafe
    -1.66
    ｃ
    -1.53
    龶
    -1.52
     pama
    -1.45
     hina
    -1.40
    }
    -1.38
    
    -1.38
     balon
    -1.37
     bloss
    -1.35
     yaka
    -1.35
    POSITIVE LOGITS
     also
    1.68
     especially
    1.54
     at
    1.44
    ulée
    1.36
    来て
    1.34
    에도
    1.34
     trabajo
    1.34
    ixante
    1.33
     here
    1.31
    arquia
    1.30
    Activations Density 0.122%

    No Known Activations