© 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. 127769
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on capitalized proper names and titles, marking character and entity names.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    names of people and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    のですか
    -1.07
    D
    -1.04
    J
    -1.02
     pooh
    -1.02
     カット
    -1.02
    P
    -1.01
    X
    -1.01
     inexorable
    -1.00
     EXHIB
    -1.00
     consig
    -1.00
    POSITIVE LOGITS
     fizer
    1.19
     herido
    1.18
    terrasse
    1.15
    jogo
    1.13
    ekw
    1.13
     with
    1.12
    wym
    1.10
    معلومات
    1.09
    MIDDLEWARE
    1.09
     bolsos
    1.08
    Activations Density 0.017%

    No Known Activations