© 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. 26522
    Prev
    Next
    INDEX
    Explanations

    mathematical equations followed by answers

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

    This neuron activates on numeric tokens—especially financial‐style numbers like stock prices, percentages, and other decimal or large integer values.

    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
     any
    -1.68
     people
    -1.54
     which
    -1.54
     Although
    -1.52
    When
    -1.50
     However
    -1.47
     When
    -1.43
    Although
    -1.43
    While
    -1.38
     unusual
    -1.38
    POSITIVE LOGITS
     perro
    1.59
     великолеп
    1.44
     lác
    1.42
     trám
    1.41
     apparaissent
    1.39
    requires
    1.37
    honestly
    1.37
     véritables
    1.35
     delightfully
    1.35
    谄
    1.34
    Activations Density 0.018%

    No Known Activations