© 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. 105638
    Prev
    Next
    INDEX
    Explanations

    words or phrases following prepositions

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

    The neuron strongly activates on relational function words—mostly prepositions and similar adpositions (e.g. “through,” “after,” “from,” “as,” “in,” “on,” “throughout”) that mark temporal or spatial relationships.

    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
     ícones
    -1.34
    嫆
    -1.34
    டும்
    -1.34
    ！！”
    -1.33
    向了
    -1.33
    浓郁
    -1.32
    鵙
    -1.30
    𓆜
    -1.29
    úš
    -1.29
     escolher
    -1.28
    POSITIVE LOGITS
     only
    1.79
     for
    1.55
     (
    1.48
    h
    1.41
     Such
    1.37
     The
    1.35
     to
    1.32
     an
    1.30
     A
    1.29
     tikai
    1.29
    Activations Density 0.087%

    No Known Activations