© 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. 9292
    Prev
    Next
    INDEX
    Explanations

    shell script file iteration

    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
     bolesti
    1.13
    !!!
    1.12
    全ての
    1.11
    lah
    1.10
     начну
    1.07
    R
    1.07
    ・・・・
    1.07
    ................
    1.03
     나의
    1.03
    eni
    1.03
    POSITIVE LOGITS
     typically
    1.69
     Обычно
    1.62
     वगैरह
    1.62
    typically
    1.58
     conventionally
    1.57
     overlaps
    1.57
     etwa
    1.54
     ordinarily
    1.54
     обычно
    1.51
    不太
    1.50
    Activations Density 0.104%

    No Known Activations