© 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. 32046
    Prev
    Next
    INDEX
    Explanations

    generated code and comments

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

    The neuron fires on code‐ and configuration‐style keywords or tags (e.g. “GENERATED,” “included,” “router.get,” “Test,” XML namespace attributes, etc.) that mark technical directives or metadata.

    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
     Give
    -0.77
     rũ
    -0.73
    ónicas
    -0.72
    ））
    -0.71
     Lokales
    -0.68
     characteristics
    -0.66
    ūra
    -0.65
     Maro
    -0.65
    Give
    -0.65
     smaller
    -0.65
    POSITIVE LOGITS
     valido
    0.69
    inig
    0.68
    pier
    0.68
    Chlor
    0.67
    Carson
    0.66
    ު
    0.66
    capitalize
    0.65
     derniers
    0.65
     ep
    0.64
     Carson
    0.64
    Activations Density 0.054%

    No Known Activations