© 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. 127836
    Prev
    Next
    INDEX
    Explanations

    mother figures

    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
    所以
    -2.56
    са
    -2.55
     schönen
    -2.39
    一生
    -2.38
     Zeitraum
    -2.34
    但
    -2.28
     vorigen
    -2.22
    -2.20
     were
    -2.19
     vorliegenden
    -2.19
    POSITIVE LOGITS
    秕
    2.52
    蟊
    2.39
     thc
    2.38
    蘩
    2.30
    ጵ
    2.14
     secreta
    2.14
    둬
    2.13
    鹪
    2.11
    끫
    2.11
     verir
    2.09
    Activations Density 0.003%

    No Known Activations