© 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. 10-GEMMASCOPE-RES-131K
    7. 65718
    Prev
    Next
    INDEX
    Explanations

    MYSQL database tables

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

    The neuron picks out the main topic or title word at the start of a new document or section.

    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
    _
    -3.23
    The
    -2.86
    </sup>
    -2.63
    *
    -2.58
    $
    -2.52
    If
    -2.52
    了一个
    -2.44
    (
    -2.42
     them
    -2.41
    &
    -2.41
    POSITIVE LOGITS
    ндарт
    2.66
    鯪
    2.44
    龉
    2.42
    縢
    2.41
    鈇
    2.36
    😙
    2.31
    靫
    2.27
    ໑
    2.27
     márm
    2.23
     manajemen
    2.22
    Activations Density 0.001%

    No Known Activations