© 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. 42493
    Prev
    Next
    INDEX
    Explanations

    trying to get something

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

    The neuron strongly detects the base verb “get” (especially in contexts of trying to obtain or achieve something).

    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
     イラストレーション
    -1.71
    椹
    -1.68
     hinzugefügt
    -1.63
    Созда
    -1.60
     demonio
    -1.60
     russo
    -1.60
     adesivos
    -1.59
    횃
    -1.56
     givet
    -1.56
    气氛
    -1.54
    POSITIVE LOGITS
     to
    2.11
     of
    1.76
     (
    1.75
     he
    1.67
     its
    1.64
     her
    1.63
     into
    1.62
     his
    1.58
    neling
    1.55
    begin
    1.54
    Activations Density 0.048%

    No Known Activations