© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14858
    Prev
    Next
    INDEX
    Explanations

    lecture events and settings

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

    The neuron activates strongly on mentions of “lecture” (and its variants like “lectures” or “lecturer”), i.e. occurrences of the word “lecture.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ส์
    -2.69
    闿
    -2.63
    艄
    -2.39
     ваше
    -2.30
    釹
    -2.28
    の概要
    -2.27
     complimented
    -2.22
    熥
    -2.13
     используя
    -2.13
    ญี่ป
    -2.13
    POSITIVE LOGITS
    .
    3.95
     The
    2.22
    》，
    2.17
     '
    2.14
    _
    2.05
    :{
    2.02
     Also
    1.98
    al
    1.97
    </h3>
    1.97
    沕
    1.93
    Activations Density 0.006%

    No Known Activations