© 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. 81531
    Prev
    Next
    INDEX
    Explanations

    site sections and features

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

    The neuron fires strongly on section‐or page‐name tokens (e.g. Home, Portfolio, Blog, Pricing, Services, Shop) that typically appear in website navigation or template menus.

    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
    IDAY
    -0.93
    PAST
    -0.84
    ︷
    -0.83
    ICIOS
    -0.82
    portál
    -0.82
    Provincia
    -0.82
    GRAFÍA
    -0.82
     गरे
    -0.81
    ganti
    -0.80
    prek
    -0.79
    POSITIVE LOGITS
     area
    1.21
    area
    0.96
     style
    0.95
    with
    0.93
     with
    0.93
    Area
    0.92
     areas
    0.92
     section
    0.88
     two
    0.86
     Section
    0.83
    Activations Density 0.023%

    No Known Activations