© 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. 127628
    Prev
    Next
    INDEX
    Explanations

    degree or qualification qualifiers

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

    The neuron activates on the adverb “reasonably.”

    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
    戆
    -2.86
    OUTUBE
    -2.75
    ⢅
    -2.69
    趼
    -2.69
    锨
    -2.66
    derdag
    -2.66
    嫫
    -2.66
    尨
    -2.64
    嗩
    -2.63
    岨
    -2.53
    POSITIVE LOGITS
    k
    3.00
    s
    2.86
    .,
    2.78
    [
    2.63
    f
    2.61
    re
    2.59
     ,
    2.55
    t
    2.53
    ",
    2.44
    n
    2.44
    Activations Density 0.002%

    No Known Activations