© 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. 70615
    Prev
    Next
    INDEX
    Explanations

    low, min, and max values

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

    The neuron responds to numeric tokens—digits, numbers, and numeric expressions 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
    ourage
    -0.93
     लेकिन
    -0.92
     больше
    -0.92
     souver
    -0.92
    stoppable
    -0.90
    toft
    -0.89
    sightly
    -0.89
    神
    -0.88
    alité
    -0.88
    aders
    -0.87
    POSITIVE LOGITS
     Mittwoch
    0.85
    Href
    0.80
     start
    0.79
    getStart
    0.78
    ঋ
    0.78
    져
    0.77
    ต่
    0.77
     kese
    0.77
    小龙
    0.76
    FileNotFound
    0.76
    Activations Density 0.012%

    No Known Activations