© 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. 71988
    Prev
    Next
    INDEX
    Explanations

    Hispanic and Latino communities

    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
    asanjo
    -2.58
     alugar
    -2.56
    作品の
    -2.47
    髕
    -2.45
    の説明
    -2.45
    嗶
    -2.39
     tresses
    -2.36
    ctuaries
    -2.33
     ガラス
    -2.33
     also
    -2.27
    POSITIVE LOGITS
    ized
    2.67
    3
    2.52
    罴
    2.48
    for
    2.47
    C
    2.38
    》，
    2.30
    ated
    2.27
    ize
    2.25
    2
    2.23
     andre
    2.22
    Activations Density 0.003%

    No Known Activations