© 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. 6737
    Prev
    Next
    INDEX
    Explanations

    blockquote, quote, or > marker

    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
     optimal
    -2.39
     other
    -2.36
     in
    -2.20
    內的
    -2.17
     more
    -2.17
     What
    -2.14
    信息的
    -2.09
    p
    -2.09
     lots
    -2.08
    }$,
    -2.05
    POSITIVE LOGITS
     Anſ
    3.17
    睃
    2.28
     nėra
    2.27
     soe
    2.27
     剧照
    2.27
     promin
    2.25
     celeb
    2.23
     Mga
    2.22
     loa
    2.22
    就在
    2.19
    Activations Density 0.001%

    No Known Activations