© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 594
    Prev
    Next
    INDEX
    Explanations

    code syntax and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    0.94
     एका
    0.78
     一
    0.77
     De
    0.73
    De
    0.73
     interacting
    0.73
    !
    0.71
     Jee
    0.70
     DE
    0.69
    бира
    0.69
    POSITIVE LOGITS
     waive
    0.78
     zár
    0.78
     نقصان
    0.77
     जिद
    0.74
    <unused1887>
    0.73
     houve
    0.72
     상세보기
    0.72
     உடனடியாக
    0.71
    ItemStack
    0.71
     Thì
    0.71
    Activations Density 0.955%

    No Known Activations