© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15034
    Prev
    Next
    INDEX
    Explanations

    common or rare disease

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

    medical texts that describe rare or common diseases and conditions with their characteristics.

    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
     on
    -1.46
     each
    -1.45
    жня
    -1.27
    ("")){
    -1.23
     kring
    -1.20
    ActionPerformed
    -1.19
    wanzig
    -1.19
    €/
    -1.18
     abusi
    -1.18
    efte
    -1.17
    POSITIVE LOGITS
     dinosaurio
    1.73
    いかがでしたか
    1.49
     ее
    1.48
    閹
    1.44
    Karakter
    1.40
     Đường
    1.40
    つづく
    1.33
     когда
    1.32
    dacia
    1.32
     её
    1.31
    Activations Density 0.454%

    No Known Activations