© 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. 1452
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    تو
    0.91
    ری
    0.76
    تش
    0.76
    ে
    0.75
    心灵
    0.73
    ط
    0.73
    正确的
    0.72
    线上
    0.71
    ход
    0.71
    i
    0.71
    POSITIVE LOGITS
     _;
    0.96
     ocurr
    0.83
     나오
    0.82
     അവര്‍
    0.81
    いた
    0.80
     asimismo
    0.80
     capítulos
    0.80
     suman
    0.78
     presses
    0.77
     __________
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.