© 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. 7954
    Prev
    Next
    INDEX
    Explanations

    coral bleaching and reefs

    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
    ます
    1.98
    ت
    1.92
    т
    1.91
    ع
    1.76
    aul
    1.74
     banquet
    1.69
    ⃣
    1.69
    п
    1.68
    ح
    1.68
    afe
    1.66
    POSITIVE LOGITS
    h
    2.22
    w
    2.16
    th
    1.91
    id
    1.90
    MSFontService
    1.80
    m
    1.80
    to
    1.78
    waf
    1.78
    vital
    1.76
    headphones
    1.73
    Activations Density 0.001%

    No Known Activations