© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92398
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical descriptions

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

    The neuron is detecting code‐file metadata and top‐of‐file declarations—things like import/include statements, copyright/license notices, and similar header items.

    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
     conformal
    -0.78
     Considerable
    -0.77
     perplexing
    -0.75
     anecdotal
    -0.73
     Herzen
    -0.72
    कृति
    -0.72
     hella
    -0.71
     hesitant
    -0.68
    ství
    -0.67
     Advertisements
    -0.67
    POSITIVE LOGITS
     Ava
    0.88
    xin
    0.87
    brei
    0.86
     leer
    0.85
     disponibles
    0.78
    kbd
    0.77
     すぐ
    0.77
    ageable
    0.76
     Sutton
    0.75
    GetObject
    0.75
    Activations Density 0.007%

    No Known Activations