© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 92945
    Prev
    Next
    INDEX
    Explanations

    cholesterol and lipids

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

    terms related to cholesterol and lipid disorders in scientific/medical contexts.

    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
     to
    -1.42
    惮
    -1.39
    mybatisplus
    -1.34
    稞
    -1.30
    moveToFirst
    -1.21
     warum
    -1.20
    brtc
    -1.20
    ureusement
    -1.19
    labus
    -1.18
     rebu
    -1.18
    POSITIVE LOGITS
     cholesterol
    1.41
    Eksterne
    1.34
     two
    1.32
    thiết
    1.31
     Präsidenten
    1.30
    ător
    1.28
     만들
    1.27
    羈
    1.27
     televisão
    1.26
    tarta
    1.26
    Activations Density 0.111%

    No Known Activations