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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 522
    Prev
    Next
    INDEX
    Explanations

    time, versions, years, names, prefixes

    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
    もありました
    -2.59
     hinder
    -2.42
    もあった
    -2.38
     ولكن
    -2.28
    と言い
    -2.25
    苙
    -2.17
    でしたが
    -2.16
    ჻
    -2.14
     embarazo
    -2.14
     zijn
    -2.13
    POSITIVE LOGITS
    t
    2.59
    We
    2.50
    Ꮔ
    2.47
    '
    2.44
     их
    2.31
     его
    2.31
    A
    2.31
     deres
    2.30
    a
    2.25
    Your
    2.17
    Activations Density 0.000%

    No Known Activations