© 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. 43923
    Prev
    Next
    INDEX
    Explanations

    self-paced learning and questionnaires

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

    This neuron responds to terms related to pacing or self-paced instruction (e.g., “self,” “paced,” “unpaced,” “pace,” “pacing”).

    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
     the
    -2.50
     is
    -2.17
     T
    -2.00
    e
    -1.79
     H
    -1.73
     On
    -1.66
     Z
    -1.63
     M
    -1.63
     touted
    -1.62
     of
    -1.54
    POSITIVE LOGITS
    ౭
    1.81
    ſſi
    1.78
    槼
    1.70
    these
    1.69
     fantasmas
    1.67
     tigre
    1.67
    埽
    1.67
    können
    1.66
    鈁
    1.66
    櫺
    1.65
    Activations Density 0.010%

    No Known Activations