© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65323
    Prev
    Next
    INDEX
    Explanations

    Chico, Bowie, Jules, Kawasaki, intellij, Fenton

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

    The neuron activates on capitalized single‐word names and branded or technical proper nouns.

    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
    s
    -2.94
    to
    -2.63
    of
    -2.61
    for
    -2.56
    en
    -2.48
    _
    -2.44
    la
    -2.33
    å
    -2.33
    able
    -2.27
     possu
    -2.25
    POSITIVE LOGITS
    '
    4.47
     Архиви
    2.58
    Possibly
    2.52
    []
    
    2.50
    nexo
    2.48
     сделал
    2.44
     estekak
    2.44
     unſ
    2.42
     to
    2.36
    istungen
    2.31
    Activations Density 0.055%

    No Known Activations