© 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. 10-GEMMASCOPE-RES-131K
    7. 40509
    Prev
    Next
    INDEX
    Explanations

    Julio or María followed by a name

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

    The neuron fires on capitalized tokens that are proper names or foreign‐language content words—especially personal names.

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

    No Comments

    Negative Logits
    tedì
    -2.58
    纐
    -2.56
    ника
    -2.52
     adelant
    -2.50
    \
    -2.44
     ако
    -2.44
     descubrir
    -2.42
     статистика
    -2.39
     famosos
    -2.38
    ﮕ
    -2.38
    POSITIVE LOGITS
    0
    3.81
    </h3>
    3.19
    For
    2.89
    or
    2.81
    $
    2.77
    In
    2.73
    </em>
    2.69
    葙
    2.55
    ”
    2.55
    ኧ
    2.52
    Activations Density 0.001%

    No Known Activations