Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8275
    Prev
    Next
    INDEX
    Explanations

    providing explanations and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
     tujuan
    0.66
    %、
    0.64
    atip
    0.63
    y
    0.63
    ని
    0.62
    ्ड
    0.62
    ි
    0.62
    ython
    0.61
    вые
    0.61
    ভাবে
    0.61
    POSITIVE LOGITS
    ير
    0.65
    η
    0.63
     laure
    0.62
     rubric
    0.58
    ize
    0.58
     bahawa
    0.57
     João
    0.56
    وی
    0.56
    چ
    0.56
     arc
    0.55
    Activations Density 0.388%

    No Known Activations