© 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. 10-GEMMASCOPE-RES-131K
    7. 10345
    Prev
    Next
    INDEX
    Explanations

    ficando / ficar

    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_10/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
    s
    -2.98
    岜
    -2.48
    炱
    -2.44
    鱻
    -2.34
    觔
    -2.19
    糶
    -2.09
    袮
    -2.08
     vitre
    -2.03
    鸸
    -2.00
    v
    -1.99
    POSITIVE LOGITS
    但我
    1.86
     crumbling
    1.83
    ...
    1.82
    '
    1.81
     больше
    1.77
     snippets
    1.77
    sonaro
    1.74
    
    1.73
    puma
    1.72
     inferences
    1.70
    Activations Density 0.001%

    No Known Activations