© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106427
    Prev
    Next
    INDEX
    Explanations

    subjective effects of substances

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

    descriptions of drug effects or psychoactive substances.

    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
    хами
    -0.89
    ποι
    -0.88
    美味しそう
    -0.82
    input
    -0.81
     exud
    -0.81
    CHAFT
    -0.80
    QtGui
    -0.80
    匂
    -0.80
     imple
    -0.80
    Encoder
    -0.79
    POSITIVE LOGITS
     effects
    1.73
     feeling
    1.43
     eu
    1.29
     effect
    1.27
     feelings
    1.27
     highs
    1.27
     euphoria
    1.26
    phoria
    1.18
     Effects
    1.13
     mellow
    1.13
    Activations Density 0.023%

    No Known Activations