© 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. 66640
    Prev
    Next
    INDEX
    Explanations

    Clark, Vivian, Yves, Erica

    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
    已经
    -2.39
    骉
    -2.33
    ↵↵
    -2.33
     specialmente
    -2.25
     行っ
    -2.19
     madd
    -2.19
     multitude
    -2.17
     パスタ
    -2.16
     unrival
    -2.14
    塍
    -2.14
    POSITIVE LOGITS
    a
    2.66
    ین
    2.56
    geſ
    2.55
    </h4>
    2.47
    </h3>
    2.41
    .
    2.41
    </h6>
    2.39
    </em>
    2.33
     And
    2.33
    »،
    2.25
    Activations Density 0.007%

    No Known Activations