© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2704
    Prev
    Next
    INDEX
    Explanations

    Go code keywords (`func`, `const`)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    -
    1.26
    Closing
    1.13
    щер
    0.98
    '
    0.95
     terceiro
    0.94
     diverting
    0.91
    Mercury
    0.90
    /
    0.86
     gracia
    0.85
    Setting
    0.85
    POSITIVE LOGITS
    觟
    1.83
    trz
    1.72
     全
    1.71
    <unused457>
    1.71
     池
    1.69
    <unused1823>
    1.65
     ด้วย
    1.64
     พร้อม
    1.62
    ije
    1.62
     夏
    1.61
    Activations Density 0.001%

    No Known Activations