© 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. 34-GEMMASCOPE-RES-131K
    4. 33140
    Prev
    Next
    INDEX
    Explanations

    by verbing

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

    The neuron fires on instances of the preposition “by.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     to
    -1.84
     that
    -1.44
     will
    -1.32
    上がった
    -1.30
     need
    -1.30
    などが
    -1.27
    みます
    -1.26
    宕
    -1.24
     cuando
    -1.21
     Итали
    -1.21
    POSITIVE LOGITS
     virtue
    2.31
     means
    2.20
     dint
    1.80
    standers
    1.71
    products
    1.60
     verdo
    1.52
     vermel
    1.41
     using
    1.41
     ondu
    1.39
    Hauptartikel
    1.39
    Activations Density 0.091%

    No Known Activations