© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57409
    Prev
    Next
    INDEX
    Explanations

    as soon as

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

    The neuron activates strongly on numeric tokens (digits or Roman numerals) such as version numbers, years, and other standalone numbers.

    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
    Research
    -0.82
    comentarios
    -0.72
    Training
    -0.71
     возгла
    -0.71
     Dames
    -0.71
    🚵
    -0.69
     genutzt
    -0.69
     Research
    -0.68
    Üdv
    -0.68
     поддержа
    -0.67
    POSITIVE LOGITS
     saves
    0.82
     save
    0.81
    ваю
    0.80
    save
    0.79
     genital
    0.76
     دنیا
    0.74
     الأح
    0.74
    saving
    0.71
    rollment
    0.69
     genera
    0.69
    Activations Density 0.028%

    No Known Activations