© 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. 34-GEMMASCOPE-RES-131K
    7. 63584
    Prev
    Next
    INDEX
    Explanations

    code attributes and structure

    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
     “
    -1.16
    appeared
    -0.98
     "
    -0.97
     Presiding
    -0.85
    这种
    -0.83
    Acciones
    -0.83
    Ejemplos
    -0.80
    ḏ
    -0.80
    appears
    -0.79
    caution
    -0.78
    POSITIVE LOGITS
     `${
    1.17
     css
    0.94
    ][
    0.91
     midt
    0.90
    ```
    0.90
    ],[
    0.89
     risorse
    0.89
    ="">
    0.88
    lė
    0.86
    ([
    0.86
    Activations Density 0.001%

    No Known Activations