© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204241
    Prev
    Next
    INDEX
    Explanations

    alcohol and its effects

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    坌
    0.39
    нкт
    0.38
     എന്നതാണ്
    0.35
    禇
    0.35
    istered
    0.35
     akik
    0.34
    栻
    0.34
     المبار
    0.34
    핑크
    0.34
    oop
    0.34
    POSITIVE LOGITS
     alcohol
    1.80
    Alcohol
    1.64
     Alcohol
    1.63
    酒
    1.63
    alcohol
    1.60
     alkohol
    1.59
     booze
    1.57
     алкого
    1.56
     alcohols
    1.55
     alcoholism
    1.52
    Activations Density 0.014%

    No Known Activations