© 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. 34-GEMMASCOPE-RES-131K
    7. 117504
    Prev
    Next
    INDEX
    Explanations

    package validate, Miltons, Anijsmelk, Effectively

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

    The neuron fires on programming‐style namespace and package identifiers (e.g. “com,” “org,” “apache,” “kafka,” “protobuf,” etc.) found in code import/package declarations.

    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
     showing
    -0.78
     considered
    -0.77
    ocytic
    -0.77
    ずみ
    -0.73
    ACIONAL
    -0.73
     mountaine
    -0.72
     词
    -0.72
     diminish
    -0.72
     swarovski
    -0.71
     PCD
    -0.70
    POSITIVE LOGITS
    Minnesota
    0.85
     Minnesota
    0.83
     جی
    0.81
    Thurs
    0.79
     Minneapolis
    0.79
    Configs
    0.78
    Agence
    0.75
     customise
    0.75
     popularidad
    0.75
     ravaged
    0.75
    Activations Density 0.010%

    No Known Activations