© 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. 128495
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on code-oriented tokens—especially technical names, version numbers, and other programming/configuration identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    lists and duration

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    mei
    -0.80
    bm
    -0.78
     가
    -0.76
    _;
    -0.76
    ալ
    -0.75
     Leuven
    -0.75
     ден
    -0.74
     machin
    -0.74
    bmp
    -0.73
    zación
    -0.73
    POSITIVE LOGITS
    赶紧
    0.97
    σεων
    0.85
     Argos
    0.82
     dessutom
    0.81
    ziosi
    0.79
     unseres
    0.78
    alimentos
    0.78
    peinture
    0.78
     our
    0.77
     esconder
    0.77
    Activations Density 0.135%

    No Known Activations