© 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. 10-GEMMASCOPE-RES-131K
    7. 119587
    Prev
    Next
    INDEX
    Explanations

    people and places

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

    The neuron strongly activates on mentions of “Estonia” (and related demonyms like “Estonian”).

    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
     This
    -2.98
    y
    -2.95
    หรือ
    -2.72
    纐
    -2.41
    
    -2.36
     nebo
    -2.27
    都快
    -2.20
     llaman
    -2.16
     работой
    -2.14
     it
    -2.11
    POSITIVE LOGITS
    </td>
    2.88
    $
    2.84
    '
    2.48
    </h6>
    2.36
    “
    2.33
     cikk
    2.23
    that
    2.22
     “
    2.20
    结语
    2.16
    ﹍﹍
    2.16
    Activations Density 0.006%

    No Known Activations