© 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. 10-GEMMASCOPE-RES-131K
    7. 111166
    Prev
    Next
    INDEX
    Explanations

    fentanyl or counterfeiting

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

    chemical compounds and drug names like fentanyl, counterfeiting prevention terms, and Fenton reagent.

    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_10/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
     =
    -3.28
    \
    -3.19
    as
    -3.02
    9
    -2.89
    1
    -2.86
    3
    -2.56
    ar
    -2.50
    8
    -2.48
    in
    -2.44
    al
    -2.41
    POSITIVE LOGITS
    zelfde
    2.77
     剧照
    2.55
    blox
    2.44
     unſ
    2.39
    ቷ
    2.34
    ╿
    2.33
     itinéraires
    2.31
    __":
    2.25
    都不会
    2.23
    struzione
    2.20
    Activations Density 0.002%

    No Known Activations