© 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. 57976
    Prev
    Next
    INDEX
    Explanations

    technical or compound terms

    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
    توض
    -1.57
     ponieważ
    -1.55
     emphasizes
    -1.40
     jugó
    -1.39
     deoarece
    -1.38
     explores
    -1.37
     dlatego
    -1.34
     because
    -1.30
     alcanzado
    -1.27
    blouse
    -1.27
    POSITIVE LOGITS
    layah
    1.34
    etzal
    1.34
    INGEN
    1.34
    ”
    1.32
    mice
    1.30
    🪝
    1.29
    fillment
    1.27
    ⾔
    1.27
    ꯏ
    1.27
     jetzt
    1.26
    Activations Density 0.070%

    No Known Activations