© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83956
    Prev
    Next
    INDEX
    Explanations

    milk and its related contexts

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

    the word "milk" and related dairy terms.

    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
     –
    -3.38
     \
    -2.95
    ですので
    -2.75
    壠
    -2.64
    ↵
    -2.63
    ’
    -2.47
    但是在
    -2.47
    但我
    -2.34
    ad
    -2.34
    <em>
    -2.34
    POSITIVE LOGITS
    ꔹ
    2.95
    
    2.95
    𐑂
    2.84
    ⑉
    2.83
    苌
    2.59
    ꯷
    2.50
    ikuti
    2.48
    ająca
    2.47
    鉭
    2.45
    endoza
    2.39
    Activations Density 0.008%

    No Known Activations