© 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. 22-GEMMASCOPE-RES-131K
    7. 93358
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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
    versus
    -1.00
     biały
    -0.94
    hio
    -0.92
     jednego
    -0.88
     Configuración
    -0.87
     moky
    -0.85
     Soporte
    -0.84
    竅
    -0.82
    nthesis
    -0.80
     örgü
    -0.80
    POSITIVE LOGITS
     futuro
    1.13
    )_/¯
    1.09
    氏が
    1.07
     gustar
    1.06
     transporta
    1.01
     vind
    1.00
     vigne
    0.97
    begin
    0.97
     Gees
    0.95
     tipis
    0.93
    Activations Density 0.016%

    No Known Activations