© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8317
    Prev
    Next
    INDEX
    Explanations

    decision making

    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
    هما
    0.79
    D
    0.77
    kk
    0.71
    P
    0.70
     nisso
    0.69
    resso
    0.67
    ಿಗ
    0.66
    C
    0.66
    =>$
    0.65
    F
    0.65
    POSITIVE LOGITS
     Thời
    0.86
    ن
    0.79
    н
    0.75
     далі
    0.73
     ওমর
    0.70
     결정
    0.70
     돈
    0.69
     感
    0.66
     요구
    0.66
    т
    0.66
    Activations Density 0.001%

    No Known Activations