© 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. 45548
    Prev
    Next
    INDEX
    Explanations

    arrangement of elements

    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
    weisungen
    -1.49
    rofoam
    -1.47
    romas
    -1.45
    もありました
    -1.40
    Якщо
    -1.38
    ИН
    -1.38
    Wenn
    -1.36
     трябва
    -1.34
     who
    -1.30
     irgendwann
    -1.30
    POSITIVE LOGITS
    怩
    1.28
    ⦑
    1.16
     Entsche
    1.15
    setFlags
    1.13
     Canadian
    1.13
     originaux
    1.12
    ILLS
    1.11
    まれ
    1.11
    лъ
    1.11
     foods
    1.11
    Activations Density 0.242%

    No Known Activations