© 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. 67399
    Prev
    Next
    INDEX
    Explanations

    mint, peppermint, basil

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

    culinary and botanical herbs or flavors, especially mint and peppermint.

    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
    s
    -2.80
    0
    -2.58
    u
    -2.11
    7
    -1.89
    4
    -1.89
    8
    -1.85
    ’
    -1.84
    在他
    -1.81
    ac
    -1.78
    在他的
    -1.78
    POSITIVE LOGITS
    nın
    1.80
    gráficas
    1.77
    趼
    1.77
    Nearly
    1.70
    Seiten
    1.70
    Према
    1.69
    água
    1.69
    ılan
    1.66
    März
    1.65
    ↵↵
    1.63
    Activations Density 0.014%

    No Known Activations