© 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. 130338
    Prev
    Next
    INDEX
    Explanations

    numbers and versions

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

    The neuron activates on numeric tokens that form software version numbers (e.g. “5.1.0” or “2.2.1”).

    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
     any
    -2.05
     want
    -1.97
     However
    -1.92
     But
    -1.84
     most
    -1.77
     when
    -1.73
     what
    -1.72
     What
    -1.69
     every
    -1.67
     one
    -1.63
    POSITIVE LOGITS
     vokal
    1.76
    Ꭳ
    1.73
     juni
    1.71
     beton
    1.58
    への
    1.58
    くちゃ
    1.57
    aing
    1.57
     radikal
    1.56
    .='
    1.55
    ?»
    1.54
    Activations Density 0.106%

    No Known Activations