© 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. 34-GEMMASCOPE-RES-131K
    7. 83379
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    This neuron activates on numeric tokens (sequences of digits), recognizing when a token is a number.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ਼
    -0.88
    ucchini
    -0.88
    Ży
    -0.77
    ▰
    -0.76
    Unters
    -0.75
     veneta
    -0.74
    我也是
    -0.73
    ضح
    -0.73
    旁邊
    -0.73
     bezpieczeństwa
    -0.72
    POSITIVE LOGITS
    thou
    0.82
    Ours
    0.82
     though
    0.81
     however
    0.80
    ▏
    0.76
    inium
    0.75
     theirs
    0.75
    滕
    0.75
    百姓
    0.73
    wage
    0.73
    Activations Density 0.329%

    No Known Activations