© 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. 22-GEMMASCOPE-RES-131K
    7. 26268
    Prev
    Next
    INDEX
    Explanations

    beginner expressing difficulty

    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
     perquè
    -1.02
     recommande
    -0.94
     απα
    -0.93
    tický
    -0.93
    termilk
    -0.92
    Coaches
    -0.92
    loggers
    -0.91
     gustó
    -0.90
    ternut
    -0.90
    ruguay
    -0.90
    POSITIVE LOGITS
     but
    1.58
     so
    1.50
     поэтому
    1.34
     this
    1.14
     I
    1.13
     therefore
    1.06
     लेकिन
    1.05
    
    1.02
     hence
    1.02
     навіть
    1.01
    Activations Density 0.102%

    No Known Activations