© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9605
    Prev
    Next
    INDEX
    Explanations

    addiction, substance abuse, and recovery

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

    sobriety and recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disperse
    0.47
     ደ
    0.43
     paprika
    0.41
     vieill
    0.39
     قاس
    0.39
     dispersed
    0.39
     dispersing
    0.38
    舒
    0.38
     Styled
    0.38
     DPI
    0.38
    POSITIVE LOGITS
     sobriety
    1.70
     addiction
    1.50
     addicts
    1.49
     sober
    1.48
     addict
    1.38
     Addiction
    1.37
     addicted
    1.30
     addictions
    1.25
     alcoholism
    1.20
     abstinence
    1.18
    Activations Density 0.288%

    No Known Activations