© 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. 72211
    Prev
    Next
    INDEX
    Explanations

    Sinai, levied, 非必要

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

    The neuron is primarily detecting proper names of institutions and organizations.

    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
    \
    -2.95
    ..."
    -2.41
    </td>
    -2.36
    k
    -2.28
    d
    -2.22
     '
    -2.20
     "
    -2.17
    am
    -2.17
     рассказала
    -2.11
    c
    -2.05
    POSITIVE LOGITS
    .'”
    2.11
     gegründet
    2.11
    ᩠
    2.09
    螄
    2.08
    䊊
    2.05
     bekende
    1.98
    鳙
    1.96
    杙
    1.96
    璆
    1.93
    が一番
    1.92
    Activations Density 0.009%

    No Known Activations