© 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. 41453
    Prev
    Next
    INDEX
    Explanations

    place names and regions

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

    The neuron fires on occurrences of the substring “conan” (in any case) within words or identifiers.

    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
    沨
    -1.98
    h
    -1.80
     They
    -1.78
    self
    -1.77
    *
    -1.76
    唠
    -1.70
     deſt
    -1.66
    ে
    -1.64
    [
    -1.63
    er
    -1.60
    POSITIVE LOGITS
    袛
    1.78
    ()];
    1.77
    眛
    1.76
    Зміст
    1.65
    widetext
    1.62
    }$
    1.61
    "];
    1.60
    AddHtmlAttribute
    1.59
    啬
    1.59
    áncer
    1.58
    Activations Density 0.008%

    No Known Activations