© 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. 130696
    Prev
    Next
    INDEX
    Explanations

    in followed by specific noun phrases

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

    This neuron detects instances of the preposition “in” immediately followed by numeric or numeric-like volume/page identifiers in academic or bibliographic citations.

    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
    très
    -1.81
     almeno
    -1.81
    鲧
    -1.77
    création
    -1.66
    grazie
    -1.64
    registrer
    -1.63
     regalías
    -1.62
    饪
    -1.60
     ongeveer
    -1.59
    
    -1.59
    POSITIVE LOGITS
     F
    1.64
     M
    1.63
     all
    1.55
    Why
    1.55
     For
    1.52
     in
    1.52
     D
    1.48
     L
    1.46
     なら
    1.42
     Another
    1.41
    Activations Density 0.194%

    No Known Activations