© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59654
    Prev
    Next
    INDEX
    Explanations

    tobacco, smoking, nicotine

    np_acts-logits-general · gemini-2.5-flash-lite

    text related to tobacco, cigarettes, and smoking.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    rations
    -0.82
    CVE
    -0.80
     hamstring
    -0.79
    rase
    -0.79
    NSURL
    -0.78
    NFS
    -0.77
     عف
    -0.75
    ldorf
    -0.74
     diarrhea
    -0.74
    oló
    -0.73
    POSITIVE LOGITS
     tobacco
    3.64
     smokers
    3.20
     cigarette
    3.20
     smoking
    3.14
     nicotine
    3.08
     cigarettes
    3.06
     Tobacco
    3.03
    Tobacco
    2.81
     smoker
    2.81
     Smoking
    2.70
    Activations Density 0.126%

    No Known Activations