© 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. 67683
    Prev
    Next
    INDEX
    Explanations

    modelmodel field definitions

    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
     it
    -1.58
     what
    -1.52
     these
    -1.38
     why
    -1.36
    に行ってきました
    -1.31
    却被
    -1.31
     seems
    -1.28
    んだから
    -1.28
     示例
    -1.27
     standar
    -1.23
    POSITIVE LOGITS
     различни
    1.44
     '
    1.42
     дъл
    1.41
    苼
    1.30
     iaitu
    1.30
     sebagainya
    1.29
    behandlung
    1.28
    unless
    1.28
     maar
    1.27
     kuiten
    1.27
    Activations Density 0.021%

    No Known Activations