© 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. 34-GEMMASCOPE-RES-131K
    7. 75459
    Prev
    Next
    INDEX
    Explanations

    exec() function calls

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

    The neuron fires on numeric tokens (integer literals or digit sequences) in the text or code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     teilnehmen
    -0.71
    від
    -0.69
    FieldError
    -0.69
    COLLECT
    -0.69
     hồi
    -0.68
     nand
    -0.67
    洲
    -0.67
    Propagation
    -0.67
    udadera
    -0.65
     balon
    -0.65
    POSITIVE LOGITS
    resses
    0.88
     Burk
    0.71
     Kro
    0.69
     озна
    0.69
    ัท
    0.68
     wrappers
    0.66
    glTex
    0.66
     الوضع
    0.65
    idata
    0.64
     mContext
    0.64
    Activations Density 0.051%

    No Known Activations