© 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. 68638
    Prev
    Next
    INDEX
    Explanations

    numbers, counts, and rankings

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

    The neuron strongly activates on numeric tokens—years, counts, measurements, and other statistical figures 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
     婚礼
    -1.00
    ólicos
    -0.99
    ختلف
    -0.92
     різних
    -0.92
     their
    -0.91
     разных
    -0.90
    bakken
    -0.88
    gás
    -0.87
    phazard
    -0.85
    ilus
    -0.83
    POSITIVE LOGITS
    Suff
    0.93
     top
    0.93
     valsty
    0.91
     régulièrement
    0.89
    thresholds
    0.87
    Mira
    0.84
    Gru
    0.84
     Top
    0.84
     ActivatedRoute
    0.84
     into
    0.83
    Activations Density 0.072%

    No Known Activations