© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14331
    Prev
    Next
    INDEX
    Explanations

    respect boundaries

    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_7_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
    ing
    2.71
    ed
    2.66
     k
    2.26
    im
    2.22
    ha
    2.21
     ha
    2.20
    ett
    1.99
     Up
    1.97
    up
    1.94
    ev
    1.93
    POSITIVE LOGITS
    ᴛ
    2.74
    Бе
    2.71
    ൃശ
    2.70
    несе
    2.66
    ్ర
    2.64
    िक्रमा
    2.63
    ޚ
    2.58
    चलिए
    2.57
    тара
    2.57
    Т
    2.55
    Activations Density 0.007%

    No Known Activations