© 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. 11673
    Prev
    Next
    INDEX
    Explanations

    numbers 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
     a
    0.62
     an
    0.52
    President
    0.50
    ra
    0.47
    Million
    0.47
    外套
    0.46
     เมตร
    0.45
     to
    0.44
     million
    0.44
    ;&#
    0.44
    POSITIVE LOGITS
    ون
    0.74
    на
    0.71
    ку
    0.68
    ни
    0.63
    ம்
    0.63
    га
    0.60
    ين
    0.60
    માં
    0.60
    ου
    0.59
    for
    0.57
    Activations Density 0.113%

    No Known Activations