© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86419
    Prev
    Next
    INDEX
    Explanations

    event gatherings and related concerns

    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
     nimmer
    -2.27
     praktisch
    -2.08
    -
    -1.90
    ໊
    -1.87
     verborgen
    -1.86
    来不及
    -1.79
     kağıdı
    -1.76
    ほうが
    -1.75
    '
    -1.75
    噲
    -1.74
    POSITIVE LOGITS
     they
    2.73
     declara
    1.93
     he
    1.88
    ),
    1.86
     knows
    1.85
     amid
    1.82
     because
    1.80
    ;
    1.79
     You
    1.74
     was
    1.73
    Activations Density 0.019%

    No Known Activations