© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38612
    Prev
    Next
    INDEX
    Explanations

    date contexts, code snippets, or proper nouns

    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
    ↵
    1.21
    ai
    1.17
    ‟
    1.15
    om
    1.13
    ap
    1.13
    나
    1.11
    era
    1.07
    ep
    1.05
    ↵↵
    1.03
    op
    1.01
    POSITIVE LOGITS
    cJ
    1.09
    screens
    1.06
    cate
    1.06
    sport
    1.05
    РА
    1.04
     conund
    1.04
     bewildered
    1.03
    萛
    1.00
    Як
    0.99
    kannya
    0.99
    Activations Density 0.000%

    No Known Activations