© 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. 62843
    Prev
    Next
    INDEX
    Explanations

    marijuana, weeds, weed control

    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
    ﾗ
    -0.93
     tracked
    -0.93
    ibatkan
    -0.80
     運
    -0.79
     goods
    -0.79
     Shoemaker
    -0.78
    cuentes
    -0.78
    限り
    -0.77
    ar
    -0.77
    FFS
    -0.77
    POSITIVE LOGITS
    killer
    1.05
    /';
    1.03
     invasive
    1.02
    /";
    0.95
    EditForm
    0.92
    /',
    0.91
    pops
    0.90
     tinham
    0.90
     tussen
    0.85
    ington
    0.84
    Activations Density 0.004%

    No Known Activations