© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117986
    Prev
    Next
    INDEX
    Explanations

    ext.view, application, invention, Q

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

    The neuron fires on numeric literals (especially version numbers and other numbers) within code snippets.

    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
    寶寶
    -0.76
    SnackBar
    -0.74
    કો
    -0.73
    Configurable
    -0.71
    からね
    -0.71
    verley
    -0.69
    Lord
    -0.69
     réservoir
    -0.68
     anonymously
    -0.68
    fast
    -0.68
    POSITIVE LOGITS
     Kuz
    0.75
    族館
    0.72
    Viewport
    0.71
    쿵
    0.71
    ux
    0.69
     viewport
    0.69
    '/>
    0.69
    isometric
    0.69
     Tablet
    0.68
     $_[
    0.67
    Activations Density 0.021%

    No Known Activations