© 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. 2530
    Prev
    Next
    INDEX
    Explanations

    turn boundary markers

    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
     haha
    1.40
    めっちゃ
    1.37
     lucu
    1.36
    쌤
    1.33
     엄마
    1.31
     hahaha
    1.28
     친구
    1.26
    haha
    1.24
    可愛い
    1.24
     Cute
    1.23
    POSITIVE LOGITS
    ,
    1.10
    (),
    0.86
    ،
    0.83
    (,
    0.77
    -,
    0.77
     consequent
    0.77
     defined
    0.76
    imposed
    0.75
     partly
    0.74
     Similarly
    0.73
    Activations Density 0.084%

    No Known Activations