© 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. 22-GEMMASCOPE-RES-131K
    7. 92895
    Prev
    Next
    INDEX
    Explanations

    mathematical notation starts

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

    This neuron detects LaTeX math‐mode symbols and variable names (especially uppercase identifiers with subscripts).

    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
     médec
    -1.49
     esmeralda
    -1.34
     boute
    -1.31
     fhew
    -1.30
     fhort
    -1.28
    ַּ
    -1.27
     Oggi
    -1.24
     fufficient
    -1.23
    おわりに
    -1.23
    vece
    -1.23
    POSITIVE LOGITS
     simplemente
    1.25
    gungen
    1.23
     not
    1.21
     hanya
    1.21
    only
    1.21
     simplement
    1.16
     únicamente
    1.16
    with
    1.13
     or
    1.12
     with
    1.11
    Activations Density 0.019%

    No Known Activations