© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    stinky, skunk, putrid, malodorous

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

    words related to bad smells, particularly forms of "stink" and related unpleasant odor descriptions.

    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
    -3.13
    ᐕ
    -2.83
    〼
    -2.80
    The
    -2.66
    镔
    -2.59
    状況
    -2.47
    能在
    -2.41
     одну
    -2.30
    ?????
    -2.28
    最初の
    -2.28
    POSITIVE LOGITS
     That
    2.97
    );
    2.81
    ),
    2.42
    ’
    2.36
     in
    2.11
     With
    2.06
    ,"
    2.03
    ↵
    2.03
     Instead
    1.98
     важно
    1.92
    Activations Density 0.002%

    No Known Activations