© 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. 76259
    Prev
    Next
    INDEX
    Explanations

    Mr. or Q:

    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
     Β
    -1.06
     আপ
    -1.05
     Лю
    -1.05
    噼
    -1.02
     Ε
    -1.00
     Κ
    -0.99
     probablemente
    -0.99
    pictured
    -0.98
     Α
    -0.98
    beit
    -0.98
    POSITIVE LOGITS
     govt
    1.19
     witcher
    1.15
     dramatist
    1.12
     till
    1.11
     ‘
    1.09
    似的
    1.06
     surety
    1.03
     bangles
    1.03
     =='
    1.03
     úl
    1.02
    Activations Density 0.003%

    No Known Activations