© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1404
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     {
    -1.41
    EReference
    -1.40
     {}),
    -1.34
    鹩
    -1.31
    );
    -1.31
     deuil
    -1.27
     إذا
    -1.24
     Universitas
    -1.24
    cur
    -1.23
     oído
    -1.23
    POSITIVE LOGITS
     for
    1.73
     at
    1.66
    nitř
    1.48
     from
    1.46
    風景
    1.35
     ample
    1.34
     What
    1.27
    navigationBar
    1.23
     such
    1.20
     것이다
    1.20
    Activations Density 0.042%

    No Known Activations