© 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. 22612
    Prev
    Next
    INDEX
    Explanations

    as if

    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
     Byzantium
    -1.18
    ingan
    -1.17
    孓
    -1.16
    licitations
    -1.15
     départements
    -1.15
    );
    -1.13
     bahia
    -1.12
    áže
    -1.09
     it
    -1.09
     框
    -1.09
    POSITIVE LOGITS
     ранее
    1.38
     Não
    1.34
     dekor
    1.33
     exklu
    1.33
     so
    1.32
     jste
    1.28
    wendi
    1.27
     ContentValues
    1.25
    كري
    1.24
     České
    1.24
    Activations Density 0.011%

    No Known Activations