© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 4510
    Prev
    Next
    INDEX
    Explanations

    live music and performances

    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_24_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
     consape
    0.54
     physicality
    0.54
     belliger
    0.53
     cautious
    0.52
     nascent
    0.52
     ១
    0.52
     conspicuous
    0.51
     negated
    0.50
     macromolecules
    0.49
    ல
    0.49
    POSITIVE LOGITS
    演奏
    0.79
     extravaganza
    0.79
    表演
    0.77
    dancing
    0.77
     спектак
    0.77
     medley
    0.73
     جشن
    0.73
    🎵
    0.72
     мероприятия
    0.71
     spotlights
    0.71
    Activations Density 0.005%

    No Known Activations