© 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. 7946
    Prev
    Next
    INDEX
    Explanations

    cotton

    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
    ج
    2.16
    ik
    1.82
    ו
    1.80
    tól
    1.79
    o
    1.78
     الميلاد
    1.75
    ના
    1.74
    ované
    1.67
     Toán
    1.67
    便是
    1.66
    POSITIVE LOGITS
    та
    2.34
    ない
    2.05
    ли
    2.00
    м
    1.96
    ों
    1.80
    रोवर
    1.76
    то
    1.73
    ं
    1.73
    ла
    1.72
    ات
    1.67
    Activations Density 0.001%

    No Known Activations