© 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. 67746
    Prev
    Next
    INDEX
    Explanations

    deity and Stephanie

    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
    d
    -3.78
    霂
    -2.58
    柃
    -2.52
    歃
    -2.52
    (
    -2.42
    m
    -2.36
    p
    -2.36
    ."
    -2.31
    .»
    -2.23
    .《
    -2.22
    POSITIVE LOGITS
     diseñados
    3.27
    になりますが
    3.03
    瓩
    2.88
     
    2.80
    </i>
    2.77
    ーーー
    2.66
    需要
    2.58
    ſelf
    2.58
    となりました
    2.53
    にかく
    2.45
    Activations Density 0.002%

    No Known Activations