© 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. 127517
    Prev
    Next
    INDEX
    Explanations

    spatio-temporal analysis

    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
     rése
    -3.03
    ᨆ
    -2.80
     články
    -2.80
     obrazy
    -2.77
     dosta
    -2.66
    祤
    -2.66
    鹟
    -2.61
     opak
    -2.56
    
    -2.53
     tunik
    -2.48
    POSITIVE LOGITS
    </em>
    3.42
    {
    2.92
    in
    2.72
    )
    2.66
    ’
    2.56
    for
    2.50
    ".
    2.44
    on
    2.41
    ,”
    2.33
    section
    2.30
    Activations Density 0.007%

    No Known Activations