© 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. 8961
    Prev
    Next
    INDEX
    Explanations

    flip switch

    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
     දැන්
    1.33
     рад
    1.23
     很
    1.19
    呀
    1.18
    これからも
    1.17
     不能
    1.14
     不是
    1.14
    侓
    1.12
     뭐가
    1.12
     น่ะ
    1.10
    POSITIVE LOGITS
    umpulkan
    1.20
    ariya
    1.10
    Characters
    1.06
     oatmeal
    1.03
     neighbouring
    1.02
    nya
    1.02
    unakan
    1.01
    Ingredients
    1.01
     characters
    1.00
    olan
    0.99
    Activations Density 0.000%

    No Known Activations