© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130963
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on numeric tokens (literal numbers and numerical expressions) in the text.

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

    xml entities and mathematical expressions

    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
    ☾
    -0.81
     influência
    -0.79
    rosse
    -0.75
    jected
    -0.75
     pewno
    -0.75
     MOON
    -0.74
    Default
    -0.73
     حيث
    -0.72
     ويت
    -0.72
     Sienna
    -0.71
    POSITIVE LOGITS
     case
    1.12
    喬
    0.96
     only
    0.96
     pesada
    0.94
     ONLY
    0.93
    乔
    0.93
    odule
    0.91
    宝
    0.90
     we
    0.89
     firmas
    0.88
    Activations Density 0.010%

    No Known Activations