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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68684
    Prev
    Next
    INDEX
    Explanations

    function or method calls

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

    This neuron activates on tokens that are part of programming namespace or library qualifiers (e.g. “Math.”, “np.”, “std::”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    を
    -2.77
    は
    -2.39
    などを
    -2.34
    などが
    -2.23
    が
    -2.22
    があり
    -2.13
    と
    -2.09
    そして
    -2.02
    がある
    -1.98
    などの
    -1.94
    POSITIVE LOGITS
    為に
    2.47
    ことも
    2.09
    ところに
    1.97
    感じで
    1.74
    様な
    1.70
    こともあり
    1.68
    さき
    1.68
    んですよ
    1.68
    ようです
    1.67
    こともある
    1.59
    Activations Density 0.008%

    No Known Activations