© 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. 64732
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and operators

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

    The neuron is specifically activating on numeric literals (numbers and number‐like 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
    IANE
    -1.06
    sunt
    -1.02
     Yves
    -0.93
    文分享
    -0.92
     flotte
    -0.91
    EVEN
    -0.91
     Cebuano
    -0.90
     证书
    -0.90
    EdgeInsets
    -0.90
    ANNE
    -0.89
    POSITIVE LOGITS
     this
    1.10
     so
    0.92
    実現
    0.88
    ៃ
    0.83
     Speisen
    0.82
     klassische
    0.80
    قدام
    0.78
    ”,
    0.78
    irement
    0.78
    luiting
    0.77
    Activations Density 0.073%

    No Known Activations