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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116203
    Prev
    Next
    INDEX
    Explanations

    juan followed by names

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

    The neuron fires on occurrences of the proper name “Juan” (and its immediate name fragments) in text.

    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
    度的
    -0.81
     ясно
    -0.78
     Probably
    -0.78
    jsk
    -0.78
    新潟
    -0.77
     उन
    -0.75
    vosť
    -0.75
     Perhaps
    -0.75
     naik
    -0.75
     fryer
    -0.73
    POSITIVE LOGITS
    ito
    1.11
    ita
    1.03
    uary
    0.94
     Bautista
    0.89
    につなが
    0.86
    Manual
    0.85
    ITA
    0.85
    LEMMA
    0.85
    illo
    0.84
     Carlos
    0.84
    Activations Density 0.009%

    No Known Activations