© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15765
    Prev
    Next
    INDEX
    Explanations

    biotechnology, MIPS, Carolina, Chrome, Obesity

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

    scientific or technical terminology, particularly names of biological compounds, geographic locations, and technical specifications.

    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
     weißem
    -1.07
    人和
    -0.94
     großem
    -0.93
     kleinen
    -0.90
    élica
    -0.88
     weißen
    -0.85
    ㅑ
    -0.85
     Corresponding
    -0.85
     vilken
    -0.84
     wydar
    -0.84
    POSITIVE LOGITS
     other
    1.11
     already
    0.96
    secutions
    0.94
    Ṫ
    0.89
     Fotografía
    0.89
     运动
    0.85
    旁邊
    0.85
     existing
    0.84
    woners
    0.84
    felf
    0.84
    Activations Density 0.090%

    No Known Activations