© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    quotation marks and brackets

    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
     Uber
    1.20
     Wo
    1.16
     Lo
    1.16
     Otto
    1.15
     W
    1.12
     Trader
    1.12
     Fi
    1.12
     AP
    1.11
     √
    1.11
     Pu
    1.11
    POSITIVE LOGITS
    finaly
    1.38
    结尾
    1.33
     dále
    1.31
     далі
    1.30
     سپس
    1.30
     następnie
    1.30
    结束
    1.27
     дальше
    1.26
     краю
    1.26
    说完
    1.26
    Activations Density 0.030%

    No Known Activations