© 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. 22-GEMMASCOPE-RES-131K
    7. 130266
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for mathematical expressions or arithmetic content (numbers, operators, equations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical questions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     begr
    -1.20
    他们
    -1.18
     verk
    -1.16
     najleps
    -1.09
     those
    -1.08
     khas
    -1.07
     salles
    -1.06
    愠
    -1.04
     ventilación
    -1.04
    ִּ
    -1.04
    POSITIVE LOGITS
     also
    1.82
    Also
    1.52
     to
    1.44
     также
    1.40
     também
    1.36
     también
    1.30
    also
    1.27
    matico
    1.24
     by
    1.21
    槇
    1.21
    Activations Density 0.087%

    No Known Activations