Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6500
    Prev
    Next
    INDEX
    Explanations

    un- prefix words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    -{
    2.20
    manship
    1.83
    人士
    1.75
    imiz
    1.70
    ούς
    1.69
    )==
    1.66
    alne
    1.65
    -{\
    1.62
     ventricle
    1.61
    es
    1.60
    POSITIVE LOGITS
    ن
    2.30
    ’
    1.96
     Declare
    1.88
    н
    1.76
     Matem
    1.71
     čega
    1.67
     siquiera
    1.65
     altres
    1.64
     Deportes
    1.61
     Differences
    1.60
    Activations Density 0.091%

    No Known Activations