© 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. 10-GEMMASCOPE-RES-131K
    7. 75725
    Prev
    Next
    INDEX
    Explanations

    and conjunctions in multiple languages

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

    The neuron detects mathematical operator symbols (e.g. “=”, “+”) in formulas.

    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
    ing
    -3.23
    焄
    -2.88
     &#
    -2.67
    ープン
    -2.67
    u
    -2.66
    3
    -2.61
    极为
    -2.45
    Surprisingly
    -2.42
    詭
    -2.39
    Väl
    -2.36
    POSITIVE LOGITS
    และ
    3.63
    埽
    3.02
    ;
    2.92
     și
    2.80
    ⚣
    2.73
    ☫
    2.70
     и
    2.66
     are
    2.61
    齶
    2.55
     và
    2.53
    Activations Density 0.004%

    No Known Activations