© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7422
    Prev
    Next
    INDEX
    Explanations

    ego

    np_acts-logits-general · gemini-2.5-flash-lite

    hypothetical scenarios and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oted
    0.55
    ger
    0.53
    dd
    0.50
    dures
    0.50
    r
    0.50
    mp
    0.49
    rt
    0.49
    lt
    0.49
    cc
    0.48
    bserv
    0.48
    POSITIVE LOGITS
    es
    0.88
    esine
    0.50
    ه‌ای
    0.48
    oine
    0.48
    .,"
    0.48
    esinin
    0.46
    électricité
    0.44
    க்கள்
    0.43
    ه‌های
    0.43
     الجديد
    0.42
    Activations Density 0.060%

    No Known Activations