© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92688
    Prev
    Next
    INDEX
    Explanations

    code and math notation

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

    This neuron fires on mathematical symbols and expressions, especially LaTeX-style variables, operators, and formula components.

    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
    ี่ป
    -0.79
    莫
    -0.75
     village
    -0.75
     Approved
    -0.72
    FECT
    -0.69
     einsetzen
    -0.68
     stimulus
    -0.67
     CHE
    -0.67
    ۱۷
    -0.67
     attractions
    -0.67
    POSITIVE LOGITS
     Moles
    0.79
    Fender
    0.77
     bénéficier
    0.77
    Frem
    0.77
     Singers
    0.76
    Tomasz
    0.73
    INNOV
    0.73
    Silvia
    0.72
    Realistic
    0.72
    Juice
    0.72
    Activations Density 0.113%

    No Known Activations