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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7589
    Prev
    Next
    INDEX
    Explanations

    highlighting key findings or concepts

    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
     YEAR
    1.02
    SAS
    1.00
    貯
    0.98
    วันที่
    0.96
    ช
    0.96
     SET
    0.95
    ปี
    0.95
    SK
    0.95
     WORKING
    0.95
    ఎ
    0.94
    POSITIVE LOGITS
    zott
    1.19
    attho
    1.13
    riqu
    1.07
    íqu
    1.05
    ódromo
    1.04
     происходит
    1.01
    rinho
    1.00
    rization
    0.99
    的就是
    0.98
    yllic
    0.98
    Activations Density 0.146%

    No Known Activations