© 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. 22098
    Prev
    Next
    INDEX
    Explanations

    food dishes and ingredients

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

    names of ethnic food dishes.

    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
     from
    -1.54
     gebunden
    -1.51
    lakukan
    -1.49
    寢
    -1.42
    kumpulan
    -1.35
     with
    -1.34
    mudah
    -1.32
    鈦
    -1.32
     those
    -1.31
     since
    -1.31
    POSITIVE LOGITS
    even
    1.45
    察觉
    1.39
    Срок
    1.34
    ⊣
    1.28
     You
    1.27
    G
    1.27
    M
    1.20
    либо
    1.20
    result
    1.20
    特殊的
    1.18
    Activations Density 0.015%

    No Known Activations