© 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. 128453
    Prev
    Next
    INDEX
    Explanations

    places and natural elements

    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
    actually
    -1.28
     månader
    -1.20
    但却
    -1.16
    了我
    -1.16
    エスト
    -1.16
     albeit
    -1.15
     actually
    -1.11
    了许多
    -1.10
     you
    -1.09
    就被
    -1.09
    POSITIVE LOGITS
    ейчас
    1.39
    آیا
    1.24
     mirar
    1.24
    kyu
    1.23
     marcadas
    1.23
     llorar
    1.21
     nordrhein
    1.20
     térm
    1.20
     encantado
    1.20
    Ār
    1.18
    Activations Density 0.077%

    No Known Activations