© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128395
    Prev
    Next
    INDEX
    Explanations

    This neuron detects standalone numeric tokens (individual digits) in the text.

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

    numbers and punctuation

    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
     nią
    -0.96
     levante
    -0.91
    announcement
    -0.89
     porcelana
    -0.89
     momenti
    -0.85
     kalem
    -0.85
     impresion
    -0.84
     апель
    -0.83
     président
    -0.82
    nove
    -0.82
    POSITIVE LOGITS
    риях
    1.17
    acionales
    1.06
    luiting
    1.04
    lagten
    1.02
     -----
    1.02
     取付
    1.00
    år
    1.00
    ̀ng
    0.96
     ...............
    0.96
     carbu
    0.96
    Activations Density 0.258%

    No Known Activations