© 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. 10-GEMMASCOPE-RES-131K
    7. 67826
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    The neuron fires on numeric tokens—digits and numeric substrings (e.g. in decimal or scientific‐notation 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_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
    锨
    -1.87
     facilita
    -1.86
    廰
    -1.80
    笮
    -1.80
    '
    -1.78
    ⇿
    -1.78
    ☆☆☆☆
    -1.77
     considere
    -1.77
     provoc
    -1.75
     requiere
    -1.75
    POSITIVE LOGITS
    They
    2.28
    It
    2.05
    3
    1.98
    它
    1.84
    СЯ
    1.84
    4
    1.80
    atação
    1.76
    8
    1.73
    when
    1.67
     Jér
    1.66
    Activations Density 0.009%

    No Known Activations