© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12264
    Prev
    Next
    INDEX
    Explanations

    foreign words and characters

    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
    呖
    -2.77
     でも
    -2.42
    ☗
    -2.36
    AutoScaleMode
    -2.28
     یک
    -2.27
     But
    -2.22
    镔
    -2.16
    ↵↵
    -2.14
     اما
    -2.11
     فهي
    -2.06
    POSITIVE LOGITS
     the
    3.05
    鬭
    2.50
    鸶
    2.39
    鮸
    2.33
    ſſen
    2.27
     trocken
    2.22
    Ꭳ
    2.20
    in
    2.17
     взгля
    2.16
    玩意
    2.16
    Activations Density 0.001%

    No Known Activations