© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98433
    Prev
    Next
    INDEX
    Explanations

    names starting with Fran or Francis

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

    This neuron is strongly activated by proper nouns—especially capitalized names of people, places, or institutions.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    脯
    -0.85
     妹
    -0.81
    ateria
    -0.81
     elabor
    -0.79
     печени
    -0.77
    ƨ
    -0.75
     declines
    -0.75
     Störungen
    -0.75
    ֹא
    -0.74
    中山
    -0.74
    POSITIVE LOGITS
    łady
    0.73
     concernant
    0.70
     которым
    0.69
    味わい
    0.69
    fitting
    0.69
    点点头
    0.69
    ActivityCompat
    0.68
    פק
    0.68
     fitting
    0.67
     **/
    0.66
    Activations Density 0.019%

    No Known Activations