© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58105
    Prev
    Next
    INDEX
    Explanations

    Harvard University

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

    The neuron fires on mentions of “Harvard” (as in Harvard University, Harvard Medical School, Harvard Business Review, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    '
    -3.03
     The
    -2.48
    比较好
    -2.42
    让我
    -2.33
     다른
    -2.27
    かっこいい
    -2.25
    カッコいい
    -2.20
     This
    -2.17
    ?"
    -2.08
    異なる
    -2.06
    POSITIVE LOGITS
    镚
    2.58
    OUTUBE
    2.52
    ﻊ
    2.41
    猡
    2.38
    which
    2.38
    裢
    2.31
    鲼
    2.30
     will
    2.20
    to
    2.20
     сможет
    2.19
    Activations Density 0.005%

    No Known Activations