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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 22
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
    ियाणा
    0.64
    anfaatkan
    0.57
    huana
    0.57
     Klima
    0.57
    蜞
    0.57
    mless
    0.57
    ruga
    0.56
    voirs
    0.55
    usages
    0.55
    kün
    0.54
    POSITIVE LOGITS
     "
    0.85
     "@
    0.77
     '@
    0.71
     "_
    0.69
     "":
    0.67
    "
    0.64
     '
    0.63
    rad
    0.63
    "@
    0.63
     complexity
    0.61
    Activations Density 0.006%

    No Known Activations