© 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. 22-GEMMASCOPE-RES-131K
    4. 36272
    Prev
    Next
    INDEX
    Explanations

    following prepositions and conjunctions

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

    This neuron responds to technical, method-and-process words in scientific writing—terms that describe procedures, dependencies, and parameter relationships (e.g. “between,” “consecutive,” “systematic,” “introduced,” “during”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     более
    -1.80
    訁
    -1.76
     limpar
    -1.70
     الحكومة
    -1.65
     использовать
    -1.63
     наиболее
    -1.55
     interrom
    -1.55
     туа
    -1.54
     была
    -1.52
    
    -1.51
    POSITIVE LOGITS
     for
    2.13
     at
    2.03
     $\
    1.62
     when
    1.56
     from
    1.55
     within
    1.48
     while
    1.42
     each
    1.41
     after
    1.40
     having
    1.40
    Activations Density 0.021%

    No Known Activations