© 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. 128802
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (integer values) in the text, i.e. it is looking for numbers.

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

    these in multiple languages

    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
     analogous
    -0.99
    ꪖ
    -0.99
    cede
    -0.96
    ৳
    -0.96
     consectetur
    -0.96
    เพิ่มเติม
    -0.96
    Likewise
    -0.96
    ributed
    -0.93
     imprimir
    -0.93
     Πολ
    -0.93
    POSITIVE LOGITS
    这些
    1.18
     these
    1.16
     etc
    1.15
    這些
    1.06
     griechischen
    0.93
     meilleure
    0.89
     aceste
    0.87
    ↵↵
    0.86
     levee
    0.84
    Museo
    0.84
    Activations Density 0.011%

    No Known Activations