© 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. 59712
    Prev
    Next
    INDEX
    Explanations

    not [verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    锘
    -1.45
    Fär
    -1.45
    坩
    -1.38
    푘
    -1.34
     ances
    -1.34
    ★☆
    -1.33
     améli
    -1.30
     épar
    -1.30
     kollu
    -1.29
     ilm
    -1.28
    POSITIVE LOGITS
     to
    1.88
    </td>
    1.62
     favourite
    1.59
    </h2>
    1.54
     if
    1.52
    it
    1.46
     还
    1.34
    洸
    1.33
     dicha
    1.31
    बी
    1.31
    Activations Density 0.057%

    No Known Activations