© 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. 886
    Prev
    Next
    INDEX
    Explanations

    what are you interested in

    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
    ी
    3.13
    ا
    2.68
    اث
    2.28
    ا۔
    2.20
    ുതി
    2.17
    י
    2.08
     (“
    2.07
     водо
    2.00
    uada
    1.97
    ה
    1.96
    POSITIVE LOGITS
    ě
    2.45
    ascimento
    2.34
    ুগত্য
    2.26
    nington
    2.24
    nel
    2.23
    ny
    2.21
    ้ํา
    2.21
    abe
    2.19
    na
    2.17
    ereal
    2.16
    Activations Density 0.188%

    No Known Activations