© 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. 44399
    Prev
    Next
    INDEX
    Explanations

    vitamin A, retinoids, acid

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

    vitamin A, retinoids, and related compounds in scientific/medical text.

    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
    ,’”
    -1.60
    鯢
    -1.59
    sibilité
    -1.52
    ’，
    -1.51
    屨
    -1.48
     indiví
    -1.46
     også
    -1.46
     splet
    -1.45
     pesso
    -1.42
     ruines
    -1.40
    POSITIVE LOGITS
     caustic
    1.55
     sagging
    1.55
     impediments
    1.53
     зді
    1.51
     Depending
    1.50
     Considering
    1.43
    אם
    1.41
    ökning
    1.39
    ými
    1.38
    orithms
    1.37
    Activations Density 0.063%

    No Known Activations