© 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. 22-GEMMASCOPE-RES-131K
    7. 38729
    Prev
    Next
    INDEX
    Explanations

    http status codes

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

    The neuron fires on numeric literals—i.e. tokens consisting of digits (numbers) 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
    yours
    -1.06
    Recomendaciones
    -0.94
    BrowserRouter
    -0.93
    是什么
    -0.93
    namt
    -0.93
    onyme
    -0.93
     Dicht
    -0.92
    moine
    -0.91
    grafías
    -0.91
    渕
    -0.91
    POSITIVE LOGITS
    точници
    0.88
    tigheter
    0.87
     a
    0.85
    Pictures
    0.85
    אני
    0.84
    ürk
    0.83
    ürü
    0.82
     local
    0.82
    Episodes
    0.81
     война
    0.81
    Activations Density 0.001%

    No Known Activations