© 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. 10-GEMMASCOPE-RES-131K
    7. 87178
    Prev
    Next
    INDEX
    Explanations

    legal documents and dates

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

    The neuron specializes in spotting numeric tokens (e.g. numbers, dates, measurements, and decimal values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    x
    -1.76
    h
    -1.76
    p
    -1.72
    f
    -1.72
    in
    -1.71
    鋲
    -1.70
     then
    -1.64
     also
    -1.61
    泠
    -1.59
     conoci
    -1.58
    POSITIVE LOGITS
    When
    1.83
    selben
    1.82
    
    1.73
    Those
    1.73
     [],
    1.71
    現在
    1.70
    tủ
    1.66
    
    1.65
    Válasz
    1.62
    März
    1.62
    Activations Density 0.004%

    No Known Activations