© 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. 67639
    Prev
    Next
    INDEX
    Explanations

    code comment markers

    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
    F
    -2.47
    d
    -2.23
    ve
    -2.11
     =
    -2.11
     for
    -2.09
    Five
    -2.06
    an
    -2.05
    G
    -2.05
    H
    -2.03
    All
    -2.02
    POSITIVE LOGITS
    鷙
    2.50
    ⅿ
    2.48
     unbelievably
    2.42
    medriver
    2.33
    𖣔
    2.30
     delightfully
    2.27
    撵
    2.27
     ‘’
    2.27
     câbles
    2.25
     あっ
    2.23
    Activations Density 0.000%

    No Known Activations