© 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. 34-GEMMASCOPE-RES-131K
    7. 76329
    Prev
    Next
    INDEX
    Explanations

    appreciation; confidence; to-do

    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
     открыть
    -1.00
     изменить
    -0.95
     caché
    -0.94
     ironically
    -0.94
     occasionally
    -0.94
     partially
    -0.92
     definitely
    -0.90
     always
    -0.90
     crudo
    -0.90
     lavander
    -0.90
    POSITIVE LOGITS
     También
    1.22
     fotografías
    1.20
     campañas
    1.19
     decenas
    1.17
     cualquiera
    1.15
     melihat
    1.10
    那我
    1.10
    竟然是
    1.09
    pregunt
    1.09
     empê
    1.08
    Activations Density 0.104%

    No Known Activations