© 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. 86875
    Prev
    Next
    INDEX
    Explanations

    distance or score

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

    The neuron fires on numeric tokens—especially decimal measurements or statistics (e.g. “within 174,” “51.5,” “27.875”)

    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
     are
    -2.81
     thre
    -2.39
    麒
    -2.38
    蟥
    -2.25
    翊
    -2.11
     остальные
    -2.09
     druga
    -2.03
     theses
    -2.03
    {
    -2.03
    enangan
    -2.00
    POSITIVE LOGITS
    s
    2.39
     että
    2.33
    </sup>
    2.22
    It
    2.20
     Some
    2.17
     メニュー
    2.02
     However
    1.99
    that
    1.98
    C
    1.95
    他
    1.92
    Activations Density 0.031%

    No Known Activations