© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27516
    Prev
    Next
    INDEX
    Explanations

    medical design software

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

    Java/programming imports related to events and UI components.

    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
     only
    -1.22
     about
    -1.14
     with
    -1.13
     pueden
    -1.13
     if
    -1.09
     based
    -1.09
     one
    -1.06
     its
    -1.05
     consists
    -1.05
     under
    -1.03
    POSITIVE LOGITS
    Tetapi
    1.13
     decorativas
    1.13
     carottes
    1.09
    könyv
    1.06
    Mereka
    1.06
     perpétu
    1.05
    ‪.‬‬
    1.05
     nia
    1.05
    妏
    1.05
    škas
    1.04
    Activations Density 0.001%

    No Known Activations