© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 871
    Prev
    Next
    INDEX
    Explanations

    been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.70
    ों
    0.69
    $,
    0.64
    y
    0.61
    rines
    0.60
    k
    0.59
    ς
    0.55
    to
    0.55
    ים
    0.54
    the
    0.54
    POSITIVE LOGITS
     been
    0.78
     Been
    0.73
    been
    0.73
    ン
    0.73
    Been
    0.68
     gotta
    0.66
     BEEN
    0.61
    न
    0.60
    auch
    0.53
     ollut
    0.52
    Activations Density 0.790%

    No Known Activations