© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103239
    Prev
    Next
    INDEX
    Explanations

    verbs indicating acquisition or action

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

    The neuron is keyed to single‐word action verbs (e.g. got, asked, used, left, get) that mark the main predicate in a sentence.

    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
    
    -1.65
    今朝
    -1.62
    本日の
    -1.54
    uttgart
    -1.52
    Siapa
    -1.51
     disponibilités
    -1.49
     pè
    -1.47
     saisons
    -1.46
     camiseta
    -1.45
    今月
    -1.45
    POSITIVE LOGITS
     to
    2.91
     of
    2.22
     from
    1.81
     about
    1.58
     they
    1.56
     against
    1.54
     mehreren
    1.51
    ”
    1.49
    ,”
    1.44
     ursprünglichen
    1.44
    Activations Density 0.047%

    No Known Activations