© 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. 1324
    Prev
    Next
    INDEX
    Explanations

    non, pre, re prefixes

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

    pre and non prefixes

    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
    Назад
    0.27
    Cré
    0.25
    및
    0.25
    Mình
    0.24
    Upon
    0.24
     безопасности
    0.24
    리오
    0.24
    ާތ
    0.24
    ۵
    0.24
    sman
    0.24
    POSITIVE LOGITS
    -
    0.44
    functional
    0.44
    -)
    0.43
    -,
    0.42
    existent
    0.41
    -]
    0.41
    context
    0.40
    -/
    0.40
    segment
    0.40
    formatted
    0.40
    Activations Density 0.475%

    No Known Activations