© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129582
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric literals (numbers or digit‐containing tokens) in the text.

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

    names and titles

    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
     guía
    -0.88
     जानकारी
    -0.87
    廚
    -0.86
     liderazgo
    -0.84
     mêmes
    -0.84
    showing
    -0.84
     délais
    -0.83
     sanitarios
    -0.83
     investissements
    -0.83
     gunakan
    -0.82
    POSITIVE LOGITS
    طاء
    0.96
    atissimo
    0.92
    шной
    0.87
     beruht
    0.87
    特典
    0.86
    putstr
    0.85
     sided
    0.84
     problems
    0.84
     DVDs
    0.83
    getTask
    0.83
    Activations Density 0.000%

    No Known Activations