© 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. 54317
    Prev
    Next
    INDEX
    Explanations

    math functions like random, round, floor

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

    This neuron detects calls to mathematical library functions or numeric‐computation methods (e.g. “Math.random,” “Math.sqrt,” “Math.log,” etc.).

    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
    -2.44
     in
    -2.13
    姪
    -2.02
    調味料
    -1.99
    方針
    -1.98
    が
    -1.95
    は
    -1.93
     ۱۱
    -1.88
     menik
    -1.84
    子は
    -1.84
    POSITIVE LOGITS
    T
    2.53
    H
    2.14
    O
    2.13
    P
    2.08
    B
    2.08
    つづく
    2.06
    為に
    2.03
    o
    2.02
    N
    2.00
    で見る
    1.98
    Activations Density 0.000%

    No Known Activations