© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40317
    Prev
    Next
    INDEX
    Explanations

    Terebra species names

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

    opening parentheses in programming code contexts, particularly in copyright notices.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects occurrences of the token sequence “jQuery(,” i.e. jQuery function calls.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otros
    -1.68
     to
    -1.63
    でもある
    -1.58
     otras
    -1.57
     outras
    -1.55
    cree
    -1.55
    出了一
    -1.53
    嵛
    -1.51
    着一个
    -1.48
    cleo
    -1.45
    POSITIVE LOGITS
    there
    2.02
    Цель
    1.76
    \
    1.60
    Причины
    1.57
    ظر
    1.54
    ۔
    1.49
    There
    1.49
    Выводы
    1.48
    e
    1.48
    Интере
    1.46
    Activations Density 0.000%

    No Known Activations