© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    WITH clauses and combine

    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_7_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
    此之外
    2.60
    txt
    2.39
     +:+
    2.34
    ಷ್ಠ
    2.27
    mip
    2.25
    ۜ
    2.25
    kové
    2.17
    yczy
    2.16
    इजेशन
    2.13
    いる
    2.13
    POSITIVE LOGITS
    ’
    2.33
     dined
    2.11
     ยัง
    2.04
    ות
    2.01
    acity
    2.00
    ‘
    2.00
    窕
    1.97
     ต
    1.91
     เพื่อน
    1.87
     Fier
    1.84
    Activations Density 0.063%

    No Known Activations