© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15578
    Prev
    Next
    INDEX
    Explanations

    Ramblings, thromboembolism

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

    words related to medical or biological terminology, particularly focusing on "thrombo" and "omb" prefixes.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    }$.
    -2.80
     が
    -2.53
    </h3>
    -2.52
    </em>
    -2.44
     embody
    -2.36
    甡
    -2.34
     Somebody
    -2.33
     на
    -2.25
     What
    -2.20
     Are
    -2.19
    POSITIVE LOGITS
    耵
    3.11
    鸶
    2.63
    塒
    2.53
    ⭏
    2.47
    .《
    2.44
     تغییر
    2.33
    s
    2.31
    ⬮
    2.28
     MILLION
    2.25
    不愿意
    2.25
    Activations Density 0.017%

    No Known Activations