© 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. 85843
    Prev
    Next
    INDEX
    Explanations

    mathematical notation followed by symbols

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

    The neuron fires on occurrences of mathematical function‐and‐map notation (e.g. single‐letter function names like “f” or “g,” the LaTeX “\$” delimiters, words like “homomorphism,” “maps,” “from,” arrows, “Hom,” 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_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
     toneladas
    -1.95
     facilitating
    -1.65
     tanques
    -1.59
     remained
    -1.57
     requerido
    -1.56
     regulador
    -1.55
     portátil
    -1.54
     suchte
    -1.54
     noteworthy
    -1.53
     bicicletas
    -1.52
    POSITIVE LOGITS
     to
    3.45
    ressing
    1.60
    me
    1.58
    )-
    1.48
    き
    1.45
     REALLY
    1.44
    ations
    1.44
     But
    1.43
     ""],
    1.43
     between
    1.41
    Activations Density 0.025%

    No Known Activations