© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130159
    Prev
    Next
    INDEX
    Explanations

    Luc Sevenhans, Hydraulic, Sleep apnoea

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

    XML elements and tags in project configuration files.

    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
     boxeo
    -1.41
     réus
    -1.30
    actéristi
    -1.27
     parfüm
    -1.26
    鐐
    -1.23
    Leírás
    -1.23
    ވ
    -1.22
    ностях
    -1.21
    Глава
    -1.20
     decoracion
    -1.20
    POSITIVE LOGITS
     that
    1.77
    ing
    1.28
     if
    1.27
     notamment
    1.20
    "
    1.20
    *
    1.17
     what
    1.16
    G
    1.16
    P
    1.14
     of
    1.13
    Activations Density 0.018%

    No Known Activations