© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108676
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

    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_34/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
     ผู้
    -0.82
     aparcamiento
    -0.81
     headline
    -0.77
     sorteo
    -0.75
    हां
    -0.74
     Bors
    -0.74
     blamed
    -0.74
     gewiß
    -0.73
    ウエスト
    -0.73
     dwie
    -0.72
    POSITIVE LOGITS
    чении
    0.82
     län
    0.82
     yako
    0.81
     грн
    0.80
    шні
    0.75
     pö
    0.75
     pemer
    0.75
    囚
    0.75
     ом
    0.75
     espel
    0.75
    Activations Density 0.000%

    No Known Activations