© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221281
    Prev
    Next
    INDEX
    Explanations

    intoxication and being drunk or high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Rename
    0.39
    긍
    0.37
    CustomerID
    0.37
    plasma
    0.36
     plasma
    0.36
    客様
    0.36
    Plasma
    0.36
    淞
    0.36
    rtype
    0.35
    KHTML
    0.35
    POSITIVE LOGITS
     intoxicating
    0.56
     intoxicated
    0.54
     drunk
    0.54
     intox
    0.52
     intoxication
    0.50
    drunk
    0.49
     drunkenness
    0.44
     endorph
    0.44
    醉
    0.44
     नशे
    0.42
    Activations Density 0.002%

    No Known Activations