© 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. 1407
    Prev
    Next
    INDEX
    Explanations

    someone doesn't agree

    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
    ار
    0.79
    را
    0.76
    م
    0.75
    ları
    0.75
    こと
    0.70
    larında
    0.70
    larla
    0.70
    la
    0.68
    まるで
    0.68
    まず
    0.67
    POSITIVE LOGITS
     (
    0.68
    s
    0.59
    aways
    0.58
     magnets
    0.58
    ")(
    0.57
     $($
    0.57
    pots
    0.57
     headsets
    0.57
     gaskets
    0.57
     Macintosh
    0.57
    Activations Density 0.782%

    No Known Activations