© 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. 22-GEMMASCOPE-RES-131K
    7. 72407
    Prev
    Next
    INDEX
    Explanations

    mathematical integration

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

    This neuron detects TeX‐style mathematical expressions (e.g. “\int”, “\sum”, indexed limits, 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
    With
    -0.90
    дакти
    -0.86
     initial
    -0.85
    手里的
    -0.85
     стал
    -0.84
     Piano
    -0.82
     первые
    -0.82
    𝘤
    -0.82
    不夠
    -0.82
     рома
    -0.81
    POSITIVE LOGITS
     Estadual
    1.07
    それは
    1.02
     Reinforced
    1.00
     posteriorly
    0.98
     DIFFERENT
    0.98
    箐
    0.96
    がありました
    0.96
    ‚¬
    0.94
     porcentual
    0.94
     SUGGEST
    0.92
    Activations Density 0.006%

    No Known Activations