© 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. 15549
    Prev
    Next
    INDEX
    Explanations

    dedication

    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
    er
    -2.34
    客様
    -2.27
    N
    -2.25
    The
    -2.22
     distintas
    -2.20
    室外
    -2.16
     सभी
    -2.16
     Once
    -2.16
     For
    -2.14
     he
    -2.11
    POSITIVE LOGITS
    ちょこ
    2.86
    久し
    2.83
    蜮
    2.53
    ほとん
    2.50
    さぁ
    2.48
    ほら
    2.48
    さあ
    2.45
    あっという
    2.44
    ↵
    2.39
     anún
    2.39
    Activations Density 0.003%

    No Known Activations