© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60459
    Prev
    Next
    INDEX
    Explanations

    mathematical and physics notation

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

    This neuron fires on standalone mathematical symbols and variable names (especially single‐letter or capitalized tokens) in formulas or LaTeX expressions.

    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
    쨩
    -1.36
    
    -1.30
    놋
    -1.30
    ŚĆ
    -1.28
    躄
    -1.27
    rition
    -1.26
    ૮
    -1.20
    thentic
    -1.20
    땃
    -1.19
    쑹
    -1.19
    POSITIVE LOGITS
     from
    1.68
     Every
    1.41
     paramount
    1.35
     every
    1.34
    just
    1.34
     Having
    1.34
     Just
    1.30
     each
    1.30
     These
    1.28
     it
    1.23
    Activations Density 0.015%

    No Known Activations