© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119338
    Prev
    Next
    INDEX
    Explanations

    waterproof mascara

    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
     gauze
    -0.81
    خدا
    -0.78
     glucos
    -0.75
     Consultancy
    -0.72
     Rond
    -0.72
    ziell
    -0.71
     Consulate
    -0.71
     redress
    -0.70
     Dropbox
    -0.70
     Balla
    -0.70
    POSITIVE LOGITS
     waterproof
    1.19
    Waterproof
    1.09
     mascara
    1.01
    waterproof
    1.00
     sm
    0.97
     Waterproof
    0.96
     mascar
    0.89
     tubular
    0.89
     lengthening
    0.88
     tubing
    0.82
    Activations Density 0.014%

    No Known Activations