© 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. 38643
    Prev
    Next
    INDEX
    Explanations

    calorie needs

    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
    ᆹ
    0.99
     exalted
    0.91
     arched
    0.82
    닙
    0.81
     escaped
    0.80
     hearts
    0.79
    это
    0.79
     апреле
    0.78
    emos
    0.78
     inferences
    0.78
    POSITIVE LOGITS
    يف
    0.79
    .
    0.78
    יות
    0.74
     nbsp
    0.74
    roqu
    0.73
     rol
    0.73
    الات
    0.70
    gj
    0.69
     dong
    0.68
    %.
    0.68
    Activations Density 0.000%

    No Known Activations