© 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-16K
    7. 2412
    Prev
    Next
    INDEX
    Explanations

    code execution and programming

    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
    ʣ
    1.16
    Además
    1.15
     WPARAM
    1.14
    Ϣ
    1.10
    <unused2145>
    1.10
     viande
    1.10
     그래서
    1.09
     Además
    1.09
    <unused2161>
    1.08
     Schön
    1.07
    POSITIVE LOGITS
     tred
    0.77
    epy
    0.75
    ek
    0.72
    eday
    0.71
    tris
    0.70
    tr
    0.70
    ard
    0.68
    isc
    0.67
     tric
    0.66
     lett
    0.65
    Activations Density 0.020%

    No Known Activations