© 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. 106184
    Prev
    Next
    INDEX
    Explanations

    celebrity names

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

    The neuron is highly sensitive to capitalized named entities—especially personal names and other proper nouns.

    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
    /
    -1.13
    ${
    -1.05
     its
    -1.02
    cooling
    -0.97
    ';
    -0.95
    ▮
    -0.95
    aturas
    -0.95
    _]
    -0.94
     suro
    -0.91
     недостатки
    -0.91
    POSITIVE LOGITS
    ausea
    0.95
    LATIN
    0.94
    Fuer
    0.93
     consecutively
    0.90
    Ново
    0.89
     former
    0.89
    textInput
    0.87
     charité
    0.86
    CAPITAL
    0.85
    gaver
    0.85
    Activations Density 0.086%

    No Known Activations