© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    running executable files

    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
    挖掘
    1.17
    লাইয়া
    1.17
    ர்த்து
    1.11
     staunch
    1.11
    <unused1653>
    1.08
    ंदोल
    1.05
    <unused328>
    1.04
    <unused632>
    1.04
    Sampling
    1.04
     vehemently
    1.03
    POSITIVE LOGITS
    ᴛ
    0.95
    edit
    0.90
    ueta
    0.90
     édition
    0.90
     dị
    0.89
    bie
    0.88
    ouette
    0.88
     occhi
    0.86
    ิ่น
    0.86
    etric
    0.85
    Activations Density 0.000%

    No Known Activations