© 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. 93195
    Prev
    Next
    INDEX
    Explanations

    kitchen exhaust hoods and splashbacks

    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
    freeze
    -0.90
     toured
    -0.86
    äldrar
    -0.80
     freeze
    -0.79
    Freeze
    -0.79
    🐐
    -0.78
     σα
    -0.78
    Freezing
    -0.77
    geladen
    -0.77
    Libre
    -0.76
    POSITIVE LOGITS
     exhaust
    1.98
     extractor
    1.65
     extraction
    1.63
     hood
    1.62
     Extraction
    1.45
    Extractor
    1.39
     extract
    1.34
    exhaust
    1.29
     exhausted
    1.29
     Exhaust
    1.27
    Activations Density 0.010%

    No Known Activations