© 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. 10-GEMMASCOPE-RES-131K
    7. 84055
    Prev
    Next
    INDEX
    Explanations

    dysfunction and damage

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

    medical or biological terms related to dysfunction, abnormality, or imbalance in bodily systems.

    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
     their
    -1.56
     a
    -1.47
     Announces
    -1.44
    िटी
    -1.36
    出了一
    -1.36
    attributed
    -1.31
     other
    -1.30
     to
    -1.30
    .)}
    -1.27
     ihrem
    -1.26
    POSITIVE LOGITS
     or
    1.66
     Hitam
    1.41
     acabo
    1.28
     или
    1.23
    ÓW
    1.22
     Putih
    1.22
     kuliner
    1.21
     muñeco
    1.20
     cewek
    1.20
    OrEmpty
    1.19
    Activations Density 0.229%

    No Known Activations