© 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-65K
    7. 40233
    Prev
    Next
    INDEX
    Explanations

    f or f followed by punctuation

    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_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
    field
    0.86
     of
    0.86
    flow
    0.82
    I
    0.81
    filed
    0.77
    phol
    0.75
    phi
    0.75
    venture
    0.73
    ol
    0.71
    ff
    0.70
    POSITIVE LOGITS
    ’
    0.84
    কে
    0.84
    ية
    0.77
    ോട്ടോ
    0.76
    </td>
    0.72
    ק
    0.70
    دوس
    0.69
     fiasco
    0.69
    🔥🔥
    0.68
    óri
    0.67
    Activations Density 1.040%

    No Known Activations