© 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. 10-GEMMASCOPE-RES-131K
    7. 44673
    Prev
    Next
    INDEX
    Explanations

    . i"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     réessayer
    -1.34
     engend
    -1.31
     поэтому
    -1.30
    ulation
    -1.30
    ئية
    -1.29
    de
    -1.27
    ں
    -1.23
    شوند
    -1.21
     например
    -1.18
    üglich
    -1.18
    POSITIVE LOGITS
     one
    1.66
     prendas
    1.29
     as
    1.27
     aislada
    1.22
    produit
    1.20
    Norge
    1.19
     will
    1.18
     captivated
    1.18
     her
    1.17
    鏤
    1.17
    Activations Density 0.004%

    No Known Activations