© 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. 114230
    Prev
    Next
    INDEX
    Explanations

    endings of names or places

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

    This neuron detects capitalized proper names and titles (i.e. named entities).

    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
     sellado
    -1.70
    对着
    -1.57
    了个
    -1.51
    了两
    -1.50
    齟
    -1.45
    蓠
    -1.44
    まって
    -1.44
    ≃
    -1.43
     sudadera
    -1.40
    違和
    -1.38
    POSITIVE LOGITS
     this
    1.81
     they
    1.70
     these
    1.64
     those
    1.45
     you
    1.41
     for
    1.38
    近期
    1.34
     that
    1.32
    最近
    1.30
     by
    1.29
    Activations Density 0.282%

    No Known Activations