© 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. 38715
    Prev
    Next
    INDEX
    Explanations

    university students

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

    The neuron activates on mentions of “university” (and closely related academic/educational institution references).

    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
    垕
    -2.98
    ⩕
    -2.70
    麁
    -2.64
     unſ
    -2.63
    僦
    -2.52
    ཥ
    -2.50
    腘
    -2.36
     .......
    -2.34
    ⚣
    -2.34
    扨
    -2.33
    POSITIVE LOGITS
    s
    3.11
    I
    3.08
    It
    3.00
    In
    2.97
    _
    2.91
    While
    2.81
    During
    2.81
    You
    2.67
    to
    2.67
    //
    2.64
    Activations Density 0.005%

    No Known Activations