© 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. 118081
    Prev
    Next
    INDEX
    Explanations

    diagrams, code, or mathematical expressions

    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
     naer
    -1.00
     mense
    -0.97
    婪
    -0.90
     Résumé
    -0.90
    !***
    -0.88
    ごま
    -0.85
     
    -0.84
     melk
    -0.84
     ‘’
    -0.84
    Pozri
    -0.84
    POSITIVE LOGITS
     каждый
    1.01
     alrededores
    0.98
    Legende
    0.95
     розта
    0.92
    ಋ
    0.91
    Maße
    0.89
     iniciales
    0.86
    část
    0.86
     джере
    0.85
     sesta
    0.85
    Activations Density 0.003%

    No Known Activations