© 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. 114085
    Prev
    Next
    INDEX
    Explanations

    in state or place

    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
    しなかった
    -1.48
     your
    -1.44
    ();*/
    -1.38
    şek
    -1.38
    </h3>
    -1.36
    providedIn
    -1.34
     caratteristiche
    -1.34
     previous
    -1.33
     swoje
    -1.32
     pierwszym
    -1.32
    POSITIVE LOGITS
     
    1.44
    )”
    1.41
     ```
    1.40
     welk
    1.31
    ardige
    1.29
     still
    1.27
    给他们
    1.27
    ).”
    1.26
    isNot
    1.26
     actualmente
    1.23
    Activations Density 0.039%

    No Known Activations