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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 5580
    Prev
    Next
    INDEX
    Explanations

    Indonesia, better than

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects mentions of mathematical operators and related numeric-constraint terms in quiz instructions.

    oai_token-act-pair · o4-miniTriggered by @drejcpesjakpesjak
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    <unused2197>
    0.90
     اہلِ
    0.88
     \...
    0.87
    <unused2174>
    0.85
    <unused2130>
    0.82
     (\"
    0.76
     кеңсеси
    0.75
    <unused2169>
    0.74
    <unused2204>
    0.73
     ẞ
    0.73
    POSITIVE LOGITS
     !!
    1.54
     ,
    1.51
     !
    1.45
    .?
    1.37
     !!!
    1.37
     !!!!
    1.36
    !!
    1.35
     .
    1.35
    .(
    1.34
    !!!!
    1.32
    Activations Density 0.558%

    No Known Activations