© 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. 21382
    Prev
    Next
    INDEX
    Explanations

    by this logic or case

    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
     februar
    -1.36
    TheReal
    -1.32
     TType
    -1.30
    льше
    -1.24
    禀
    -1.21
    лича
    -1.21
    闿
    -1.20
    maxHeight
    -1.17
    kumpulan
    -1.16
    Kus
    -1.16
    POSITIVE LOGITS
     then
    1.86
    Then
    1.41
     next
    1.35
     therefore
    1.32
     Then
    1.32
     either
    1.27
    then
    1.25
     Zeitpunkt
    1.23
    If
    1.23
    oner
    1.23
    Activations Density 0.038%

    No Known Activations