© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32630
    Prev
    Next
    INDEX
    Explanations

    number and letter combinations

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

    This neuron responds to tokens that contain digits (i.e. alphanumeric strings or numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    すっ
    -1.35
    あっという
    -1.31
    事も
    -1.29
    Aç
    -1.29
     weiteren
    -1.29
     nuestras
    -1.23
    GillaGilla
    -1.23
    inerario
    -1.18
    美味しそう
    -1.17
    ことも
    -1.16
    POSITIVE LOGITS
    v
    1.21
     in
    1.13
     has
    1.09
     even
    1.02
    R
    1.01
     data
    1.00
    x
    1.00
    が
    0.98
     name
    0.98
    WAUKEE
    0.98
    Activations Density 0.022%

    No Known Activations