© 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. 22-GEMMASCOPE-RES-131K
    4. 9665
    Prev
    Next
    INDEX
    Explanations

    places, organizations, and countries

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

    The neuron selectively activates on mentions of the chemical “peroxide” (i.e. compound names ending in “-oxide,” especially “peroxide”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    culares
    -0.90
    ידה
    -0.83
     Witt
    -0.82
    aringan
    -0.82
    new
    -0.81
     wspar
    -0.81
    cookieParser
    -0.81
     areia
    -0.81
    eler
    -0.81
     młod
    -0.81
    POSITIVE LOGITS
    直至
    0.83
    maktadır
    0.80
    довая
    0.79
     deltag
    0.77
    銠
    0.77
    entador
    0.76
     spørsmål
    0.75
    eBay
    0.75
    ᵘ
    0.75
    syste
    0.75
    Activations Density 0.221%

    No Known Activations