© 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. 129667
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numerical tokens (sequences of digits), i.e. it spots numbers or numeric literals in the text.

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

    latitude, longitude, monetary values

    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
     that
    -1.02
    onnaise
    -1.01
    ǃ
    -0.96
     animación
    -0.89
    ⫹
    -0.88
     Verkehrs
    -0.85
    /
    -0.84
     lopen
    -0.82
    čke
    -0.81
     Bürgermeister
    -0.80
    POSITIVE LOGITS
    corresponding
    0.76
     ее
    0.75
    分页
    0.73
     moron
    0.73
    TIN
    0.73
     rst
    0.72
     ukraine
    0.72
     соответству
    0.72
    ligent
    0.71
    Caro
    0.71
    Activations Density 0.057%

    No Known Activations