© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21665
    Prev
    Next
    INDEX
    Explanations

    native place names

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

    This neuron detects the adjective “native” when used to indicate a person’s place of origin.

    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
     there
    -2.00
     where
    -1.82
    There
    -1.77
    What
    -1.61
    Even
    -1.59
     nawet
    -1.59
     it
    -1.59
    When
    -1.53
     two
    -1.52
    Where
    -1.48
    POSITIVE LOGITS
    astify
    1.51
    lijst
    1.47
    3
    1.46
    2
    1.41
     of
    1.41
    "]));
    1.38
    ꔹ
    1.38
    us
    1.38
    CEAN
    1.38
    vidades
    1.34
    Activations Density 0.101%

    No Known Activations