© 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. 12-GEMMASCOPE-2-RES-262K
    7. 3510
    Prev
    Next
    INDEX
    Explanations

    URLs and links

    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
    ят
    0.89
    お
    0.79
    sns
    0.77
    ли
    0.73
    k
    0.73
    té
    0.71
    ющую
    0.70
    :
    0.70
    യ
    0.69
    я
    0.69
    POSITIVE LOGITS
     retard
    0.88
     Приступљено
    0.82
     Þ
    0.82
     irritation
    0.82
     Malik
    0.79
     COMPLET
    0.79
     REI
    0.79
     regained
    0.79
     stale
    0.78
     ฟ
    0.77
    Activations Density 0.001%

    No Known Activations