© 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. 64161
    Prev
    Next
    INDEX
    Explanations

    vaping and eliquid

    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
     rain
    -0.91
     raster
    -0.78
    EPS
    -0.75
     vulnerable
    -0.71
     router
    -0.71
     drugs
    -0.71
     vulnerability
    -0.71
    rase
    -0.70
    Vul
    -0.70
     ski
    -0.69
    POSITIVE LOGITS
     vape
    2.56
     vaping
    2.44
     Vape
    2.33
     Vap
    2.06
     vap
    2.02
    vap
    1.91
     vapor
    1.89
     vapour
    1.87
    vape
    1.84
     nicotine
    1.70
    Activations Density 0.021%

    No Known Activations