© 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. 58232
    Prev
    Next
    INDEX
    Explanations

    works perfectly / worked fine

    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
     posiblemente
    -1.45
     wcześ
    -1.41
     surla
    -1.41
    薮
    -1.39
    艿
    -1.38
    новение
    -1.38
    вгений
    -1.37
     evtl
    -1.34
    struttura
    -1.31
     znacz
    -1.30
    POSITIVE LOGITS
     various
    1.33
    昨日は
    1.32
    今日の
    1.28
    本日は
    1.27
    不同
    1.23
     different
    1.23
    本日の
    1.20
    1.20
     every
    1.20
     not
    1.17
    Activations Density 0.137%
    No Known Activations