© 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. 32149
    Prev
    Next
    INDEX
    Explanations

    Documentation structure markers

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

    This neuron responds to code‐like tokens—such as XML namespace prefixes, CamelCase identifiers, escaped characters (e.g. “\n”), and numeric literals—marking programming or markup syntax.

    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
    """
    -0.85
    oció
    -0.83
    𝒙
    -0.81
    "+"
    -0.80
    {\$
    -0.79
    டை
    -0.78
    lož
    -0.78
     krä
    -0.77
     Huis
    -0.77
     jardin
    -0.77
    POSITIVE LOGITS
    icrous
    0.80
     storico
    0.75
     cresce
    0.74
     anciens
    0.73
     ensued
    0.71
    opcion
    0.71
     csak
    0.70
     CN
    0.70
    Suerte
    0.70
     LIS
    0.69
    Activations Density 0.000%

    No Known Activations