© 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. 28980
    Prev
    Next
    INDEX
    Explanations

    incarcerated or foreclosure or hepatocytes

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

    words related to cellular biology, incarceration, or geographic locations, particularly those with specialized medical or scientific terminology.

    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
    ጺ
    -2.72
    And
    -2.66
    foreignKey
    -2.56
     και
    -2.55
     và
    -2.41
     และ
    -2.41
    ඍ
    -2.39
    y
    -2.31
    Of
    -2.30
    The
    -2.27
    POSITIVE LOGITS
    ↵
    3.73
     but
    2.59
    ↵↵
    2.48
     $\
    2.39
    悒
    2.22
     satış
    2.17
    日曜日
    2.16
    愎
    2.14
    俱乐
    2.06
    师父
    2.06
    Activations Density 0.007%

    No Known Activations