© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21111
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

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

    The neuron is detecting numeric literals (numbers) in the code.

    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
     kemudian
    -1.91
    岖
    -1.87
     Einstellungen
    -1.81
     pioggia
    -1.75
     umy
    -1.73
     spiaggia
    -1.72
    ırl
    -1.65
    راهن
    -1.63
     短发
    -1.62
     direita
    -1.59
    POSITIVE LOGITS
    It
    2.19
    pography
    2.13
    曁
    1.97
    You
    1.93
     –
    1.88
    [
    1.86
    annuation
    1.78
    r
    1.73
    ”
    1.73
     rápido
    1.71
    Activations Density 0.029%

    No Known Activations