© 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. 16612
    Prev
    Next
    INDEX
    Explanations

    he/She acts

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

    This neuron detects the main subject of a biographical passage—i.e. the proper name and its accompanying pronouns referring back to that person.

    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
     tendrán
    -1.02
     by
    -1.02
    タワー
    -0.95
     thriving
    -0.91
    になれる
    -0.90
    ‘
    -0.88
     people
    -0.87
     at
    -0.87
     provavelmente
    -0.85
    おば
    -0.84
    POSITIVE LOGITS
     and
    2.31
    และ
    1.36
    和
    1.28
     maupun
    1.02
    ousand
    1.02
    journalist
    1.01
    quares
    0.99
    および
    0.97
     вместе
    0.95
     beiden
    0.94
    Activations Density 0.034%

    No Known Activations