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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1921
    Prev
    Next
    INDEX
    Explanations

    Python code or text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    род
    0.79
    ی
    0.78
    іль
    0.76
    nali
    0.74
    GAMMA
    0.73
    اب
    0.71
    دي
    0.69
    بول
    0.69
    Կ
    0.69
    ди
    0.67
    POSITIVE LOGITS
     devised
    0.80
     earnestly
    0.75
    的和
    0.75
    regation
    0.74
     감소
    0.73
     tirelessly
    0.73
     깊
    0.71
     하는데
    0.70
     상세
    0.70
    ೫
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.