© 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. 47705
    Prev
    Next
    INDEX
    Explanations

    Fitzgerald, ListAdapter, roaring

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

    The neuron strongly activates on capitalized proper names or unique named entities (e.g. people, places, book titles).

    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
    塒
    -2.31
    なんとなく
    -2.19
     meriva
    -2.11
     auffi
    -2.08
    .")]
    -2.06
    鶿
    -2.06
    哢
    -2.05
     LIVES
    -2.05
    纐
    -2.05
     ビキニ
    -2.02
    POSITIVE LOGITS
    ’
    2.78
     In
    2.30
     for
    2.25
     time
    2.22
     &#
    2.17
     During
    2.16
     unrelenting
    2.11
    !
    2.05
    e
    2.03
     so
    2.02
    Activations Density 0.003%

    No Known Activations