© 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. 81452
    Prev
    Next
    INDEX
    Explanations

    applying sprays and coatings

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

    instructions about applying or coating substances to surfaces.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on descriptions of applying or spraying a liquid (e.g. spray, application, applied, inoculated) onto a surface.

    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
    //!
    
    -0.94
    (!_
    -0.94
    mtable
    -0.89
    cla
    -0.84
    po
    -0.84
    パード
    -0.84
    endes
    -0.82
    su
    -0.81
    不同
    -0.81
    os
    -0.81
    POSITIVE LOGITS
     on
    1.91
     onto
    1.76
     around
    1.49
     großzü
    1.48
     over
    1.43
     directly
    1.37
     liberally
    1.34
     sparingly
    1.30
    ทั่ว
    1.22
     across
    1.15
    Activations Density 0.033%

    No Known Activations