© 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. 34-GEMMASCOPE-RES-131K
    7. 62573
    Prev
    Next
    INDEX
    Explanations

    special character names

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

    The neuron fires on individual numeric characters (digits), identifying tokens that are 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ОК
    -0.80
     тук
    -0.79
     פֿ
    -0.79
    が進
    -0.78
    իվ
    -0.78
     turf
    -0.77
    ceding
    -0.77
    燃費
    -0.75
    projected
    -0.75
    部长
    -0.74
    POSITIVE LOGITS
    леку
    0.88
    ੯
    0.85
     Gestion
    0.84
     masker
    0.80
    DataURL
    0.78
    建
    0.77
    Squad
    0.76
    ▎
    0.75
    Triangles
    0.74
     torchvision
    0.73
    Activations Density 0.005%

    No Known Activations