© 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. 22-GEMMASCOPE-RES-131K
    7. 26290
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

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

    The main thing this neuron does is detect numeric literals (numbers) in code or 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
    mão
    -0.87
    щая
    -0.81
     informative
    -0.79
    umbered
    -0.77
    块钱
    -0.77
     Ausdrücke
    -0.76
    些
    -0.76
     पू
    -0.75
     important
    -0.75
    Ин
    -0.75
    POSITIVE LOGITS
    apj
    0.93
    gmd
    0.89
     کردیم
    0.86
    VertexBuffer
    0.83
     variasi
    0.82
     famí
    0.78
    𝗒
    0.77
    ッテ
    0.77
    お互
    0.77
     electrico
    0.75
    Activations Density 0.004%

    No Known Activations