© 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. 64939
    Prev
    Next
    INDEX
    Explanations

    import

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

    This neuron fires on programming-language tokens—identifiers, keywords, symbols, and other syntax elements typical of source 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_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
     REPLACE
    -0.92
    installation
    -0.88
    devise
    -0.87
    𝕐
    -0.85
     jamais
    -0.84
    US
    -0.83
    álise
    -0.82
     guida
    -0.82
     được
    -0.82
    ulturen
    -0.81
    POSITIVE LOGITS
     guestbook
    0.93
    たび
    0.86
     tässä
    0.84
     lisäksi
    0.84
    のが
    0.83
    禛
    0.82
     réservoir
    0.81
     chauffage
    0.79
     übrigens
    0.79
     liburan
    0.79
    Activations Density 0.049%

    No Known Activations