© 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. 114153
    Prev
    Next
    INDEX
    Explanations

    Terri Lynn Erickson

    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
     smitten
    -1.23
     satunya
    -1.20
     风格
    -1.16
     Væ
    -1.15
     związane
    -1.15
     漂亮
    -1.14
     Pozn
    -1.10
     now
    -1.10
     geschafft
    -1.10
    2
    -1.09
    POSITIVE LOGITS
    </h5>
    1.42
    Tämä
    1.20
     jedoch
    1.20
    </h4>
    1.19
    </u>
    1.18
     tidak
    1.16
    /}
    1.16
    ()>
    1.16
     وكان
    1.16
    openModal
    1.15
    Activations Density 0.028%

    No Known Activations