© 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. 34-GEMMASCOPE-RES-131K
    7. 59059
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts

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

    This neuron fires on tokens that belong to formal mathematical notation or LaTeX‐style math expressions (e.g. symbols like “$”, “\Gamma”, “\mathbb”, and specialized algebraic terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     коме
    -0.78
    ◅
    -0.72
    commentId
    -0.71
     REPUBLIC
    -0.70
    Cours
    -0.69
     głowy
    -0.68
    StoredProcedure
    -0.67
     Lawyer
    -0.67
     testing
    -0.66
    карта
    -0.65
    POSITIVE LOGITS
     motive
    0.92
     motives
    0.80
     Motive
    0.79
    FRO
    0.79
    DR
    0.78
     انگی
    0.75
    alogie
    0.75
     motiv
    0.73
     DR
    0.72
    PHY
    0.71
    Activations Density 0.043%

    No Known Activations