© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93423
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and symbols

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

    The neuron activates on standalone numeric tokens (i.e. sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     if
    -1.76
     (
    -1.66
     in
    -1.55
     which
    -1.45
     because
    -1.41
     from
    -1.40
     without
    -1.34
     before
    -1.32
     after
    -1.28
     januar
    -1.26
    POSITIVE LOGITS
    ⓒ
    1.45
     verschillende
    1.38
    УДК
    1.29
    這些
    1.25
     sommige
    1.23
    久し
    1.22
    遊んで
    1.22
     arşivlendi
    1.20
     alcune
    1.16
     marvelous
    1.16
    Activations Density 0.006%

    No Known Activations