© 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. 11428
    Prev
    Next
    INDEX
    Explanations

    in followed by connective phrases

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

    The neuron fires on the preposition “in” when it appears in formal multiword legal or administrative phrases (e.g. “in response to,” “in conjunction with,” “in accordance with”).

    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
    这里
    -1.56
     {
    -1.50
    Даже
    -1.49
     these
    -1.45
    Хотя
    -1.45
     any
    -1.40
     time
    -1.36
    는
    -1.36
     there
    -1.33
     timpul
    -1.32
    POSITIVE LOGITS
    Analyte
    1.61
     zoals
    1.49
     Voraussetzung
    1.45
    ?"
    1.39
    crum
    1.36
     intric
    1.34
     Besonder
    1.32
     addition
    1.31
    ."
    1.31
     escuro
    1.29
    Activations Density 0.121%

    No Known Activations