© 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. 108693
    Prev
    Next
    INDEX
    Explanations

    section titles or list items

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

    The neuron strongly activates on programming‐language code fragments (recognizing code keywords, symbols, and 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
    Some
    -0.87
     純
    -0.82
     some
    -0.82
     mexicana
    -0.78
    [,
    -0.76
     ymax
    -0.76
    Array
    -0.75
     corpi
    -0.75
     Assumptions
    -0.75
     Some
    -0.74
    POSITIVE LOGITS
    ibig
    0.93
     asiatique
    0.92
     retrovisor
    0.91
     asesinato
    0.81
    racha
    0.81
     Nachbar
    0.80
     perpé
    0.79
     neighboring
    0.79
     coloridos
    0.78
     sélectionnez
    0.77
    Activations Density 0.035%

    No Known Activations