© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100240
    Prev
    Next
    INDEX
    Explanations

    time and place prepositions

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

    The neuron strongly activates on the preposition “in,” marking phrases that specify locations or times (e.g., “stayed in,” “set in,” “was held in”).

    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
     The
    -1.77
     проблема
    -1.73
    KommentareTeilen
    -1.59
     cercana
    -1.52
     многих
    -1.48
    って思
    -1.48
     attorno
    -1.41
     Hinblick
    -1.40
     grabar
    -1.39
    ์ตูน
    -1.38
    POSITIVE LOGITS
    你这
    1.41
    ists
    1.41
    ization
    1.38
    rogens
    1.38
    each
    1.35
     キーホルダー
    1.34
    . 
    1.34
     of
    1.33
     玩具
    1.33
    盌
    1.31
    Activations Density 0.001%

    No Known Activations