© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67100
    Prev
    Next
    INDEX
    Explanations

    or alternatives in multiple languages

    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
    s
    -1.86
    馐
    -1.80
    蔸
    -1.77
     &
    -1.76
    thodon
    -1.75
    éramos
    -1.73
     rau
    -1.72
    y
    -1.68
     lakini
    -1.68
     mily
    -1.68
    POSITIVE LOGITS
     determinadas
    1.91
    𖣘
    1.91
     вовсе
    1.84
     verzichten
    1.82
     capacidades
    1.80
     Еще
    1.80
     thậm
    1.80
     者
    1.79
    ↵↵
    1.79
     puede
    1.77
    Activations Density 0.027%

    No Known Activations