© 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. 8492
    Prev
    Next
    INDEX
    Explanations

    oil and fat

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

    references to cooking or food oils, particularly in recipes or culinary 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_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
    in
    -1.61
    ”
    -1.53
    on
    -1.51
    (
    -1.45
     nei
    -1.39
     nih
    -1.36
    l
    -1.36
    c
    -1.35
     in
    -1.32
    quelize
    -1.30
    POSITIVE LOGITS
     Projektu
    1.52
     мы
    1.47
     Если
    1.46
     Когда
    1.46
     получили
    1.45
    thiết
    1.41
     berkunjung
    1.41
     dvě
    1.38
     provocando
    1.38
     When
    1.38
    Activations Density 0.075%

    No Known Activations