© 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. 47919
    Prev
    Next
    INDEX
    Explanations

    italian, cubana, or chinese

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

    The neuron fires on locative language—tokens that mark spatial relations or positions (e.g. prepositions like “in,” “on,” “above,” copular verbs “was,” “be,” and related context words).

    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
     then
    -1.94
     of
    -1.63
     to
    -1.51
    cadeau
    -1.47
     confirmación
    -1.47
     Detalles
    -1.45
     salvación
    -1.38
     reunião
    -1.37
     promoción
    -1.35
     Consejos
    -1.34
    POSITIVE LOGITS
    writerow
    1.41
     asta
    1.26
    </h1>
    1.23
     cubana
    1.23
    agrave
    1.13
    為主
    1.11
     aka
    1.10
     intrigue
    1.09
     ३
    1.09
     italian
    1.08
    Activations Density 0.008%

    No Known Activations