© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 933
    Prev
    Next
    INDEX
    Explanations

    pepper and peppercorns

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

    mentions of "pepper" in various contexts, including the spice, product names, and proper nouns.

    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
    翃
    -3.09
     geringe
    -2.88
     úrov
    -2.81
    銠
    -2.80
    in
    -2.78
     véritable
    -2.78
    梛
    -2.67
     avec
    -2.67
    出售
    -2.66
     pomoci
    -2.64
    POSITIVE LOGITS
     When
    3.23
    </td>
    2.88
     From
    2.81
    which
    2.72
     By
    2.59
    Nearly
    2.58
     touted
    2.53
    </h2>
    2.52
     It
    2.45
    嫱
    2.45
    Activations Density 0.002%

    No Known Activations