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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3920
    Prev
    Next
    INDEX
    Explanations

    Wildcats

    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
    له
    0.89
    នៃការ
    0.86
     هە
    0.79
    شه
    0.77
    诹
    0.77
    starcore
    0.76
    вање
    0.76
     تحقیقات
    0.75
    ক
    0.75
    الله
    0.74
    POSITIVE LOGITS
    '
    1.02
    ated
    0.83
    sb
    0.79
    Õ
    0.79
    ate
    0.75
    \'
    0.74
    TA
    0.73
    h
    0.73
    ian
    0.73
    ATED
    0.73
    Activations Density 0.000%

    No Known Activations