© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92766
    Prev
    Next
    INDEX
    Explanations

    water coolers and air conditioners

    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
     充電
    -0.84
     injectors
    -0.73
     caliper
    -0.71
    love
    -0.71
    bine
    -0.70
     Recycling
    -0.70
    Statics
    -0.69
     gutters
    -0.66
     盒
    -0.66
    diam
    -0.66
    POSITIVE LOGITS
     cooler
    1.09
     Cooler
    0.87
     coolers
    0.82
     water
    0.79
    CURLOPT
    0.78
     Cool
    0.78
    unsaturated
    0.77
    Cooler
    0.75
    cooler
    0.75
    Cool
    0.73
    Activations Density 0.012%

    No Known Activations