© 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. 48367
    Prev
    Next
    INDEX
    Explanations

    XML and code components

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

    The neuron detects numeric tokens (integers or decimals) 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_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
     çünkü
    -1.98
     metoda
    -1.93
     pesso
    -1.82
     anjo
    -1.80
     incrí
    -1.78
    饹
    -1.72
     весен
    -1.70
    𓆏
    -1.64
     flota
    -1.63
     también
    -1.63
    POSITIVE LOGITS
     включая
    1.72
     including
    1.67
     or
    1.64
    ка
    1.59
     you
    1.56
    hetically
    1.54
     You
    1.54
    neling
    1.53
    мпер
    1.48
     Wartawan
    1.47
    Activations Density 0.002%

    No Known Activations