© 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. 8091
    Prev
    Next
    INDEX
    Explanations

    trace amounts of gases or metals

    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
    いっぱい
    2.23
    い
    1.89
    ב
    1.83
    𝖊
    1.82
    α
    1.81
    我相信
    1.79
    辕
    1.78
    Código
    1.72
    🎆
    1.68
    ول
    1.66
    POSITIVE LOGITS
    e
    2.75
    y
    2.33
    er
    2.19
    a
    2.16
    ad
    2.09
    p
    2.05
    on
    2.00
    et
    1.90
    ‌ای
    1.89
    or
    1.84
    Activations Density 0.004%

    No Known Activations