© 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. 22-GEMMASCOPE-RES-131K
    7. 34440
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron activates on numeric and arithmetic‐operator tokens in mathematical 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_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
     extensive
    -1.39
     difficult
    -1.30
     high
    -1.27
     low
    -1.27
     large
    -1.25
     specific
    -1.23
     N
    -1.21
     unusually
    -1.21
     highly
    -1.20
     more
    -1.18
    POSITIVE LOGITS
    และ
    1.53
     všechny
    1.41
     impecable
    1.39
     BECAUSE
    1.32
    骉
    1.31
     และ
    1.27
    Technologie
    1.23
    或者是
    1.21
     BEAUTIFUL
    1.18
    なぜ
    1.17
    Activations Density 0.098%

    No Known Activations