© 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. 71295
    Prev
    Next
    INDEX
    Explanations

    website navigation Home

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

    This neuron is triggered by website navigation or breadcrumb interface elements (like “Home,” “You are here,” menu labels, and separators).

    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
     藏
    -1.20
     dormitorio
    -1.13
    至尊
    -1.12
    '
    -1.11
     When
    -1.11
    жели
    -1.07
    ﹝
    -1.07
     hjälper
    -1.07
    Frat
    -1.05
     behulp
    -1.04
    POSITIVE LOGITS
     vecchio
    1.34
    must
    1.30
     him
    1.28
    ַע
    1.27
     soste
    1.27
     специалистов
    1.24
    new
    1.20
    ୈ
    1.20
     nawet
    1.20
    important
    1.19
    Activations Density 0.088%

    No Known Activations