© 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. 128486
    Prev
    Next
    INDEX
    Explanations

    pitfalls and shortcomings and spectral

    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
     веке
    -2.61
     飾
    -2.38
    鷸
    -2.11
    );
    -2.03
    𝑃
    -2.02
     */
    -1.98
     \
    -1.96
     {
    -1.95
    )
    -1.94
    Он
    -1.94
    POSITIVE LOGITS
    ༷
    2.59
    媄
    2.48
    鸶
    2.44
     Ubicación
    2.42
     jejich
    2.36
    
    2.34
     Garantía
    2.31
     Artículos
    2.28
    ᯾
    2.28
     Producción
    2.22
    Activations Density 0.006%

    No Known Activations