© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    institution, program, generation, Europe

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

    The neuron fires on the main content words (especially nouns and technical or topic‐specific terms) in a passage.

    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
    轳
    -3.02
     to
    -2.56
    などに
    -2.30
     descub
    -2.28
     it
    -2.25
     efectu
    -2.22
     kısa
    -2.22
     \&
    -2.19
    mpagne
    -2.14
     sebagian
    -2.13
    POSITIVE LOGITS
    𓋼
    2.78
    b
    2.77
    us
    2.73
    i
    2.42
    ﹍﹍
    2.41
     various
    2.34
    Цитата
    2.34
    婓
    2.31
    From
    2.23
     untuk
    2.23
    Activations Density 0.023%

    No Known Activations