© 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. 22262
    Prev
    Next
    INDEX
    Explanations

    physical structures or exit points

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

    The neuron fires specifically on the token “outlet” (including its plural/form variations) wherever it appears in the text.

    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
     スクール
    -2.69
    鲠
    -2.39
     -
    -2.39
    ,.
    -2.38
    in
    -2.36
    i
    -2.34
    ant
    -2.30
    with
    -2.28
    w
    -2.27
    ’
    -2.20
    POSITIVE LOGITS
    𓆜
    3.23
    揷
    2.81
    咵
    2.81
    dzić
    2.77
    珦
    2.75
    萏
    2.67
    鲀
    2.66
    ྵ
    2.64
     helicóptero
    2.64
    時間は
    2.64
    Activations Density 0.004%

    No Known Activations