© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35416
    Prev
    Next
    INDEX
    Explanations

    magnitude change

    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_22/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
    ριο
    -1.11
    都已经
    -1.02
     kefir
    -1.01
     desplazamiento
    -0.98
     persec
    -0.96
     réserver
    -0.94
    嵓
    -0.94
     previos
    -0.92
    
    -0.91
     hotelu
    -0.90
    POSITIVE LOGITS
     when
    1.23
     in
    1.15
     without
    1.14
     not
    1.13
     double
    0.97
     with
    0.95
     so
    0.93
     put
    0.92
     remove
    0.89
     knock
    0.88
    Activations Density 0.334%

    No Known Activations