© 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. 10-GEMMASCOPE-RES-131K
    7. 112841
    Prev
    Next
    INDEX
    Explanations

    Main menu

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

    The neuron strongly activates on the standalone, capitalized word “Main,” as used in section headers or titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -1.75
    .
    -1.66
    geſ
    -1.66
     лицом
    -1.59
    ,”
    -1.59
    <
    -1.57
    ílica
    -1.49
    垕
    -1.49
     you
    -1.45
    我们将
    -1.43
    POSITIVE LOGITS
    傒
    2.19
    o
    2.09
    骉
    2.00
    
    1.95
     Infór
    1.92
     Mainly
    1.80
     ส์
    1.80
    というのが
    1.68
    をかけ
    1.67
    ことの
    1.62
    Activations Density 0.020%

    No Known Activations