© 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. 10-GEMMASCOPE-RES-131K
    7. 22465
    Prev
    Next
    INDEX
    Explanations

    operators <= and >=

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

    The neuron detects occurrences of the LaTeX “\le” (less-than-or-equal-to) command in the text.

    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
    孓
    -2.97
    鸰
    -2.48
    勦
    -2.45
     untuk
    -2.42
     pneu
    -2.38
    ၟ
    -2.36
    嵙
    -2.30
    "> 
    -2.30
    踯
    -2.30
    ophageal
    -2.28
    POSITIVE LOGITS
    "
    3.00
    ↵
    2.94
    er
    2.77
     .
    2.69
     '
    2.41
    ,.
    2.31
    ,,
    2.27
     are
    2.23
    (
    2.20
     
    2.13
    Activations Density 0.002%

    No Known Activations