© 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. 20697
    Prev
    Next
    INDEX
    Explanations

    shared preceding configuration or data nouns

    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
     The
    -2.25
    那你
    -2.23
     houve
    -2.14
     houver
    -2.11
     precisamos
    -2.08
     wspania
    -2.06
     trabaj
    -2.06
     Of
    -1.98
    方に
    -1.97
    ↵
    -1.95
    POSITIVE LOGITS
    ൎ
    2.69
    Ꭳ
    2.42
    ጺ
    2.41
    縯
    2.36
    ｇ
    2.33
    ة
    2.30
     Pièces
    2.27
     glyphicon
    2.27
    .–
    2.23
     rosario
    2.23
    Activations Density 0.004%

    No Known Activations