© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15340
    Prev
    Next
    INDEX
    Explanations

    features and functionality

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    because
    -1.52
     because
    -1.41
     eight
    -1.37
     أيض
    -1.19
    يًا
    -1.17
    خذ
    -1.13
     ukuran
    -1.09
    UserDTO
    -1.09
    ၈
    -1.08
    when
    -1.06
    POSITIVE LOGITS
     features
    1.83
     functionality
    1.55
     permettant
    1.38
    的功能
    1.38
     you
    1.37
     기능
    1.37
     feature
    1.36
     function
    1.33
     fonction
    1.32
     brasileiros
    1.32
    Activations Density 0.053%

    No Known Activations