© 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. 22-GEMMASCOPE-RES-131K
    7. 12863
    Prev
    Next
    INDEX
    Explanations

    in/on/at followed by location, time, or activity

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

    The neuron strongly activates on common English function words—especially the prepositions “in,” “at,” “on,” and “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_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
    といいます
    -1.31
     geburtstag
    -1.23
    也就是说
    -1.20
     
    -1.20
    iskt
    -1.16
    有两
    -1.10
     perfeitamente
    -1.09
     sonhos
    -1.08
     direto
    -1.08
     filha
    -1.07
    POSITIVE LOGITS
    Зміст
    1.19
     dollari
    1.12
    ificato
    1.10
     Senza
    1.09
    〰
    1.09
     (!__
    1.06
     Handlungen
    1.05
    TRIBUTES
    1.02
    seamnă
    1.02
    тером
    0.99
    Activations Density 0.034%

    No Known Activations