© 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. 124603
    Prev
    Next
    INDEX
    Explanations

    data set

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

    The neuron fires strongly on mentions of datasets (e.g. “data set,” “dataset,” or “data sets”).

    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
    鹪
    -2.34
    蕺
    -2.09
    罴
    -2.06
    禤
    -2.03
    泺
    -1.98
    嫱
    -1.95
     itinéraire
    -1.88
    訐
    -1.84
    1
    -1.82
    趿
    -1.80
    POSITIVE LOGITS
     untuk
    2.44
    \
    2.23
    ation
    2.22
    ar
    2.17
    in
    2.14
    (
    2.02
     representantes
    1.93
    :
    1.92
    ところが
    1.90
    ين
    1.89
    Activations Density 0.009%

    No Known Activations