© 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. 22-GEMMASCOPE-RES-131K
    7. 104476
    Prev
    Next
    INDEX
    Explanations

    PER CURIAM

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

    This neuron fires on numeric tokens (numbers) 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_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
    が
    -2.50
     to
    -2.34
     on
    -2.23
     in
    -2.23
     from
    -2.13
    c
    -2.09
    を
    -1.97
    e
    -1.88
     for
    -1.87
    〜。
    -1.84
    POSITIVE LOGITS
    すっ
    2.55
    為に
    2.47
    に入れる
    2.45
    ところに
    2.42
    えっ
    2.41
    久し
    2.38
    に入れ
    2.36
    凄く
    2.30
    感じで
    2.25
    ビックリ
    2.23
    Activations Density 0.001%

    No Known Activations