© 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. 28134
    Prev
    Next
    INDEX
    Explanations

    . Posted The initial Methods Published

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

    The main thing this neuron does is detect numeric tokens (digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     thái
    -0.85
     verranno
    -0.82
     Nascimento
    -0.81
    宝石
    -0.80
     linkovi
    -0.79
     eux
    -0.79
    ℑ
    -0.77
    графи
    -0.77
    клу
    -0.77
    дели
    -0.77
    POSITIVE LOGITS
     valoraciones
    0.92
    specifically
    0.91
     marrom
    0.90
    número
    0.85
    "}"
    0.83
    throughout
    0.83
     prioridad
    0.82
     insanların
    0.82
    mostly
    0.81
     conclusiones
    0.81
    Activations Density 0.375%

    No Known Activations