© 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. 34-GEMMASCOPE-RES-131K
    7. 59496
    Prev
    Next
    INDEX
    Explanations

    spray, mist

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Sap
    -0.74
     soap
    -0.73
    sap
    -0.73
     Sap
    -0.70
     Hamp
    -0.70
    Sar
    -0.68
     Tub
    -0.68
     sắp
    -0.67
    ว
    -0.67
     riguarda
    -0.66
    POSITIVE LOGITS
     spray
    3.89
     Spray
    3.38
    Spray
    3.31
     spraying
    3.23
     sprays
    3.16
    spray
    3.11
     sprayed
    3.02
     mist
    2.69
     sprayer
    2.36
    喷
    2.31
    Activations Density 0.017%

    No Known Activations