© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12838
    Prev
    Next
    INDEX
    Explanations

    Angelina Jolie, Oscar Goldman, neoplasm

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

    proper names, especially names of people, in various languages.

    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
    (
    -3.02
    AL
    -2.97
     gewisse
    -2.56
     EVEN
    -2.30
    佯
    -2.23
     haupts
    -2.20
     se
    -2.16
    苳
    -2.16
     deines
    -2.16
    ',
    -2.14
    POSITIVE LOGITS
    </strong>
    3.16
    </h3>
    2.28
     Hinblick
    2.20
    ?”
    1.99
     biała
    1.98
    𝑈
    1.97
    縈
    1.96
     waarvan
    1.95
    嫵
    1.94
    ？！
    1.88
    Activations Density 0.004%

    No Known Activations