© 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. 45259
    Prev
    Next
    INDEX
    Explanations

    static aviation events

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

    The neuron strongly fires on the uppercase “header” tokens and dateline or section‐heading words (e.g. source names, all‐caps titles and metadata at the top of newswire stories).

    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
    кат
    -0.82
    Scrolled
    -0.75
     aliquot
    -0.72
     ම
    -0.72
    ylvania
    -0.71
     cesty
    -0.71
    urie
    -0.69
     vacaciones
    -0.69
     motyw
    -0.69
    Экономи
    -0.68
    POSITIVE LOGITS
     static
    1.86
    Static
    1.65
     Static
    1.56
    static
    1.44
     display
    1.43
    静态
    1.36
     displays
    1.27
     STATIC
    1.25
    Display
    1.22
     Display
    1.22
    Activations Density 0.033%

    No Known Activations