© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45711
    Prev
    Next
    INDEX
    Explanations

    sky survey measurements

    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
    Negative Logits
     that
    -1.59
     ended
    -1.20
     everyone
    -1.16
    </h5>
    -1.16
     ersche
    -1.13
     дѣ
    -1.13
    */
    -1.13
    íteni
    -1.13
    </h3>
    -1.12
    もお
    -1.10
    POSITIVE LOGITS
    дати
    1.21
    瘫
    1.17
     Calories
    1.14
     productores
    1.13
    猝
    1.13
    发生了
    1.11
    дав
    1.09
     电视
    1.09
     beset
    1.08
    pherds
    1.07
    Activations Density 0.073%

    No Known Activations