© 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. 45685
    Prev
    Next
    INDEX
    Explanations

    Preliminary evidence

    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
    Negative Logits
    da
    -1.96
    ;
    -1.82
    o
    -1.77
    ha
    -1.77
    ke
    -1.75
    ’
    -1.67
    r
    -1.67
     Although
    -1.66
    ter
    -1.66
    ly
    -1.66
    POSITIVE LOGITS
    不
    2.09
     ganzen
    1.81
    豳
    1.77
     különböző
    1.77
    理
    1.74
    
    1.72
     növény
    1.70
    xnn
    1.68
    NEY
    1.68
     stratég
    1.67
    Activations Density 0.000%

    No Known Activations