© 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. 69242
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and set membership

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

    The neuron fires on inline mathematical notation—variable names, numerals, and LaTeX/math‐symbol tokens enclosed in $…$.

    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
     Bemerkungen
    -0.97
     herausgegeben
    -0.97
     Nähr
    -0.94
     система
    -0.93
     Academy
    -0.91
     święta
    -0.91
     kérdés
    -0.91
    Academy
    -0.88
    かれて
    -0.88
    borderSide
    -0.87
    POSITIVE LOGITS
     like
    1.15
     Procure
    1.07
     personally
    1.04
     calientes
    1.01
    Each
    1.01
    ILITIES
    1.00
    LANDS
    1.00
    ANTED
    1.00
    There
    0.96
    ･･
    0.96
    Activations Density 0.037%

    No Known Activations