© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    accidental harm or negative consequences

    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
    ς
    2.17
    স
    1.88
     mẽ
    1.87
    ט
    1.79
    s
    1.73
     leider
    1.67
     guise
    1.63
     saga
    1.63
    ׁ
    1.59
    ής
    1.55
    POSITIVE LOGITS
    ва
    1.97
    anın
    1.93
    p
    1.77
    阊
    1.77
    td
    1.72
    transistors
    1.71
    se
    1.67
    g
    1.66
     polymorphisms
    1.60
    theta
    1.59
    Activations Density 0.011%

    No Known Activations