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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 570
    Prev
    Next
    INDEX
    Explanations

    code structures

    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_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
    “-
    1.10
    ျေး
    1.00
    ”-
    0.97
    霝
    0.94
    -”
    0.93
    %"
    0.92
     প্রতিফল
    0.88
    -%
    0.86
    -"+
    0.86
    -{\
    0.83
    POSITIVE LOGITS
     सनातन
    1.13
    ;
    1.00
    io
    0.97
    agem
    0.93
    ,
    0.91
     =
    0.90
     equals
    0.89
     можливо
    0.89
    ouilles
    0.86
    inel
    0.86
    Activations Density 0.139%

    No Known Activations