© 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. 34-GEMMASCOPE-RES-131K
    7. 65077
    Prev
    Next
    INDEX
    Explanations

    digestive health and problems

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

    content related to the digestive system and digestive processes.

    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_34/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
    ̳
    -0.83
    eniu
    -0.82
    Dirty
    -0.82
    둥
    -0.81
    \|_{\
    -0.80
     vap
    -0.79
     répertoire
    -0.78
    mă
    -0.77
    jimo
    -0.74
     моро
    -0.73
    POSITIVE LOGITS
     digestion
    3.56
     digestive
    3.20
     digest
    2.81
     Digestion
    2.50
    diges
    2.25
     DIGEST
    2.22
     digesti
    2.20
    消化
    2.19
     stomach
    2.17
     digested
    2.13
    Activations Density 0.031%

    No Known Activations