© 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. 22-GEMMASCOPE-RES-131K
    7. 25148
    Prev
    Next
    INDEX
    Explanations

    et collaborators

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

    This neuron detects names of researchers (authors) typically appearing in citation contexts.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ajouté
    -1.13
     полностью
    -1.12
     может
    -1.05
     envoyé
    -1.05
     annoncé
    -1.05
    に対する
    -1.05
     isn
    -1.05
     beschä
    -1.04
    各種
    -1.03
    点点
    -1.02
    POSITIVE LOGITS
     Cedex
    1.28
    licante
    1.20
    PubMed
    1.18
    pinMode
    1.16
    jand
    1.13
    🎯
    1.12
    čnih
    1.09
    等人
    1.08
     ő
    1.06
     Mexique
    1.06
    Activations Density 0.041%

    No Known Activations