© 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. 130976
    Prev
    Next
    INDEX
    Explanations

    wide variety of

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

    The neuron activates on words expressing variations or assortment—e.g. “variety,” “diversity,” or “wide variety of.”

    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
     navide
    -1.77
    纛
    -1.74
    涐
    -1.70
     presumably
    -1.60
    <bos>
    -1.55
     defunct
    -1.54
    过来了
    -1.53
    aticano
    -1.49
    borderSide
    -1.49
    但他
    -1.47
    POSITIVE LOGITS
     of
    2.53
     
    1.96
     If
    1.87
     ถ้า
    1.78
     yine
    1.73
    LECTIONS
    1.67
     när
    1.59
    痒
    1.59
     if
    1.59
    la
    1.55
    Activations Density 0.015%

    No Known Activations