© 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. 48454
    Prev
    Next
    INDEX
    Explanations

    illegal drugs and substances

    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
     infancia
    -0.79
    த்து
    -0.78
     converts
    -0.78
    ecin
    -0.77
    騷
    -0.75
    驱
    -0.75
     Converts
    -0.74
     ultras
    -0.73
     autoradio
    -0.72
     sprink
    -0.70
    POSITIVE LOGITS
     drugs
    2.63
     substances
    2.09
     illegal
    1.96
    drugs
    1.81
     substance
    1.76
     drug
    1.73
     Drugs
    1.70
     recreational
    1.68
     street
    1.62
     illicit
    1.62
    Activations Density 0.057%

    No Known Activations