© 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. 10-GEMMASCOPE-RES-131K
    4. 99762
    Prev
    Next
    INDEX
    Explanations

    studies about groups were undertaken

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

    The neuron fires on language describing research methods and participant data (e.g. analyzing data, participants’ ages, being asked, researchers at X institution).

    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
     this
    -1.73
     is
    -1.30
     now
    -1.26
     circum
    -1.22
     such
    -1.20
    QWidget
    -1.20
     himself
    -1.18
     it
    -1.17
     being
    -1.16
    Dieser
    -1.14
    POSITIVE LOGITS
    Their
    1.45
    ご連絡
    1.41
    她們
    1.39
     которые
    1.37
     también
    1.36
     study
    1.33
     who
    1.31
     faisaient
    1.29
     sẽ
    1.28
     außerdem
    1.28
    Activations Density 0.543%

    No Known Activations