© 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. 34-GEMMASCOPE-RES-131K
    7. 1190
    Prev
    Next
    INDEX
    Explanations

    proper nouns and numbers

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

    The neuron strongly activates on numeric tokens (e.g. dates, years, counts, and other digit strings) in the text.

    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
    :
    -1.77
     by
    -1.54
     in
    -1.52
     M
    -1.49
     as
    -1.47
     G
    -1.46
     that
    -1.45
     L
    -1.45
     The
    -1.45
     B
    -1.43
    POSITIVE LOGITS
    ↵↵
    1.65
     étan
    1.59
     empêcher
    1.54
     reseña
    1.46
     funciones
    1.40
    푉
    1.38
    
    1.38
    Buna
    1.37
    haften
    1.36
     maneras
    1.36
    Activations Density 0.021%

    No Known Activations