© 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. 15610
    Prev
    Next
    INDEX
    Explanations

    deal

    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
     \
    -2.78
    ༀ
    -2.64
    趼
    -2.45
     červen
    -2.42
     Geruch
    -2.36
     šed
    -2.27
    ⢅
    -2.25
    "];
    -2.22
    旄
    -2.22
    ⇸
    -2.17
    POSITIVE LOGITS
     was
    3.13
    Our
    2.72
     deal
    2.42
     lancia
    2.42
    容易
    2.31
    la
    2.31
    っぷり
    2.30
    ؟
    2.20
    le
    2.20
    ra
    2.17
    Activations Density 0.016%

    No Known Activations