© 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. 60870
    Prev
    Next
    INDEX
    Explanations

    English words

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

    The neuron chiefly activates on numeric tokens (i.e. digits and number-like strings).

    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
    一项
    -0.80
    Appendices
    -0.77
     Glossary
    -0.75
    photos
    -0.75
    Traducción
    -0.75
     Geor
    -0.75
     martes
    -0.74
    ੜ
    -0.73
     vâ
    -0.73
    写真を
    -0.72
    POSITIVE LOGITS
     text
    2.17
     texts
    2.14
     documents
    1.85
     corpus
    1.48
     document
    1.48
     articles
    1.46
    text
    1.45
    Text
    1.41
     текста
    1.40
     sentences
    1.38
    Activations Density 0.050%

    No Known Activations