© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99005
    Prev
    Next
    INDEX
    Explanations

    invites nominations, new app, picture of

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

    The neuron responds to numeric tokens (sequences of digits) 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
    Maybe
    -0.81
     European
    -0.78
     військо
    -0.78
     resurrected
    -0.77
     perpetually
    -0.77
     Aboriginal
    -0.75
     incessant
    -0.74
     in
    -0.73
     Maybe
    -0.73
     facilitates
    -0.73
    POSITIVE LOGITS
    сение
    0.98
     kinda
    0.93
     .......
    0.91
     .........
    0.91
    ఽ
    0.90
     viſ
    0.88
    naio
    0.88
     😁
    0.87
     COUNTRY
    0.86
     порта
    0.85
    Activations Density 0.012%

    No Known Activations