© 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. 10-GEMMASCOPE-RES-131K
    4. 12532
    Prev
    Next
    INDEX
    Explanations

    in a way, in a sense

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

    This neuron specializes in picking up the hedging/discourse‐marker phrase “in a way” or “in a sense.”

    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
     Fassung
    -1.77
    汌
    -1.69
    冏
    -1.57
     freaking
    -1.54
     diseñadores
    -1.52
    ",
    
    -1.51
    你和
    -1.46
     and
    -1.45
     ternyata
    -1.45
    ゆったり
    -1.45
    POSITIVE LOGITS
     it
    1.93
     of
    1.79
     «
    1.66
     springfox
    1.58
     that
    1.57
    ifes
    1.55
    t
    1.51
     ця
    1.46
     what
    1.44
     haces
    1.41
    Activations Density 0.004%

    No Known Activations