© 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. 44855
    Prev
    Next
    INDEX
    Explanations

    argumentative essay, application context, no pathologically

    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
    т
    0.86
    letic
    0.78
     gosh
    0.78
    들은
    0.75
    다
    0.75
     yapmış
    0.74
     bomb
    0.73
     ხოლო
    0.73
     cropping
    0.73
     respect
    0.72
    POSITIVE LOGITS
    remainder
    0.83
    timezone
    0.74
    &=
    0.73
    degrees
    0.73
    GAR
    0.71
    Procedure
    0.70
    哪個
    0.70
    timestep
    0.69
    ีก
    0.68
    duplicates
    0.68
    Activations Density 0.000%

    No Known Activations