© 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. 65125
    Prev
    Next
    INDEX
    Explanations

    webcomics, code, financial data

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

    The neuron fires on numeric literals (integers or decimals) 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_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
     what
    -2.44
     each
    -1.90
     that
    -1.85
     one
    -1.74
     as
    -1.72
     with
    -1.72
     before
    -1.63
     both
    -1.60
     there
    -1.58
     the
    -1.57
    POSITIVE LOGITS
    罴
    1.84
    튿
    1.72
     ส์
    1.66
    klád
    1.63
    ⽅
    1.62
     siè
    1.59
    扨
    1.59
    蚡
    1.55
    栊
    1.55
    ꪳ
    1.54
    Activations Density 0.267%

    No Known Activations