© 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. 22-GEMMASCOPE-RES-131K
    7. 27513
    Prev
    Next
    INDEX
    Explanations

    Sierra Leone

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

    The neuron activates on capitalized proper nouns—place names, organization titles, and 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_22/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
     сахара
    -1.17
     if
    -1.14
    {*}
    -1.12
    ruik
    -1.09
     légiti
    -1.07
     émotion
    -1.07
    高知
    -1.03
    ⓧ
    -1.03
    AMPTON
    -1.02
     déplo
    -1.02
    POSITIVE LOGITS
     gewerb
    1.10
     actualizada
    1.08
    他们
    1.08
     Geschä
    1.06
    ocirc
    1.06
    جوی
    1.05
    ENTLY
    1.05
     данного
    1.04
     females
    1.04
    They
    1.03
    Activations Density 0.001%

    No Known Activations