© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11135
    Prev
    Next
    INDEX
    Explanations

    on a chart or graph

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

    The neuron primarily detects large multi-digit numeric values (especially in the thousands).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    commas in lists of amenities, features, or items.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of displaying or presenting data visually, such as through maps, charts, tables, or graphs.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    mouseover
    0.64
    량
    0.60
    ACKNOWLEDGMENTS
    0.59
    netbeans
    0.58
    الث
    0.58
     நடத்த
    0.58
    ້ອຍ
    0.57
    絮
    0.57
    кту
    0.57
    зку
    0.57
    POSITIVE LOGITS
     director
    0.54
    alpha
    0.52
     rapper
    0.50
     if
    0.50
     whereby
    0.50
    꼈
    0.49
     whether
    0.49
     Callahan
    0.49
     Wochschr
    0.49
     Consolidated
    0.49
    Activations Density 0.000%

    No Known Activations