© 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. 130503
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric tokens—any standalone numbers or numeric expressions.

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

    overall range and limits

    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
     inmediata
    -0.83
     escritor
    -0.82
    cinhas
    -0.81
     možnost
    -0.81
     rígido
    -0.79
     detaylı
    -0.79
    Reklama
    -0.79
    спеди
    -0.79
    Обе
    -0.79
    して下さい
    -0.78
    POSITIVE LOGITS
    总
    0.94
     total
    0.92
     overall
    0.92
     общего
    0.91
    TOTAL
    0.91
    xlim
    0.90
    整个人
    0.89
     começo
    0.88
     entire
    0.85
    身形
    0.85
    Activations Density 0.085%

    No Known Activations