© 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. 102596
    Prev
    Next
    INDEX
    Explanations

    attention to detail

    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
     Vordergrund
    -1.50
    ;
    -1.39
    然后
    -1.38
    ߝ
    -1.38
    <bos>
    -1.37
    voltaic
    -1.34
    phemy
    -1.31
     внешний
    -1.30
     Kø
    -1.30
    錮
    -1.27
    POSITIVE LOGITS
    𖤐
    1.58
     it
    1.44
    6
    1.42
     while
    1.41
    gráficas
    1.39
    cedores
    1.38
     perfection
    1.38
     mentre
    1.37
    eſ
    1.37
    ard
    1.36
    Activations Density 0.003%

    No Known Activations