© 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. 31-GEMMASCOPE-2-RES-262K
    7. 53182
    Prev
    Next
    INDEX
    Explanations

    'f' before 'avorable', 'actions', or list items

    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_31_width_262k_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
     of
    0.90
    field
    0.89
    filed
    0.79
    flow
    0.78
    I
    0.77
    ?
    0.75
    ff
    0.73
    фии
    0.73
    phol
    0.72
    phi
    0.71
    POSITIVE LOGITS
    কে
    0.84
    ية
    0.79
    ’
    0.78
    ോട്ടോ
    0.75
    ج
    0.73
    ק
    0.72
    ро
    0.71
    ್
    0.71
    
    0.71
     interno
    0.70
    Activations Density 0.146%

    No Known Activations