© 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. 34-GEMMASCOPE-RES-131K
    7. 86774
    Prev
    Next
    INDEX
    Explanations

    technical code identifiers

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

    The main thing this neuron does is detect numeric tokens (numbers and digit sequences) anywhere 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_34/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
    Was
    -0.80
    ViewSet
    -0.77
     apparently
    -0.75
     which
    -0.74
    おきます
    -0.73
     unable
    -0.73
    Orang
    -0.73
     настолько
    -0.72
    علن
    -0.72
    Which
    -0.72
    POSITIVE LOGITS
    dangerous
    0.91
    xem
    0.85
     Iyer
    0.83
    Zurück
    0.80
    ٥
    0.78
     Brito
    0.78
     separado
    0.77
     torsdag
    0.76
    equip
    0.76
    晧
    0.76
    Activations Density 0.026%

    No Known Activations