© 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. 34-GEMMASCOPE-RES-131K
    7. 62646
    Prev
    Next
    INDEX
    Explanations

    places and categories

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

    The neuron is a detector for capitalized named‐entity tokens (proper nouns such as people’s names, organizations, places, and titles).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    氪
    -0.73
    阚
    -0.72
     helfen
    -0.71
    クリート
    -0.67
     odeur
    -0.66
    ulipas
    -0.65
     Albanian
    -0.65
    ''');
    -0.65
     उन्होंने
    -0.64
    ハル
    -0.64
    POSITIVE LOGITS
     Botswana
    1.92
     Gabor
    1.61
    Botswana
    1.48
    🇧
    1.21
     Bots
    1.11
    Bots
    1.01
     Bats
    0.96
     Mme
    0.94
     Mots
    0.89
    ┬
    0.89
    Activations Density 0.011%

    No Known Activations