© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5400
    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
     sleeve
    0.76
    MUR
    0.74
    ic
    0.71
    ুয়ার
    0.71
    ❮
    0.70
     decomp
    0.68
     Тому
    0.68
    AUR
    0.67
    লা
    0.66
    LAR
    0.66
    POSITIVE LOGITS
    觓
    1.01
    ାଇ
    0.86
     войне
    0.84
    پيديا
    0.82
     บ่
    0.82
     dibuj
    0.79
     parejas
    0.79
     थकान
    0.79
    ب
    0.79
    ấp
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.