© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11131
    Prev
    Next
    INDEX
    Explanations

    opioids, fentanyl, heroin

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

    mentions of drugs, particularly opioids, alcohol, tobacco and related substances of abuse.

    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_22/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
     necessidades
    -1.36
     vantagens
    -1.20
     espirituales
    -1.19
    I
    -1.19
    g
    -1.18
     forças
    -1.16
     esenciales
    -1.16
     ações
    -1.13
     dianteiro
    -1.11
    h
    -1.11
    POSITIVE LOGITS
    ಇ
    1.66
    ಆ
    1.59
    paket
    1.46
     actrice
    1.44
     constater
    1.37
    ಅ
    1.35
     مساء
    1.34
    Ḳ
    1.32
    Extremely
    1.31
     faciliter
    1.31
    Activations Density 0.054%

    No Known Activations