© 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. 86736
    Prev
    Next
    INDEX
    Explanations

    resources and components

    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
     each
    -1.10
     one
    -1.02
     bebés
    -1.02
     mengucap
    -1.01
     Hưng
    -0.97
     visage
    -0.96
     six
    -0.94
    rrrrrrrr
    -0.94
     setempat
    -0.94
     soirée
    -0.93
    POSITIVE LOGITS
     représenter
    1.05
    ızı
    1.03
     entonces
    1.02
     Đ
    1.02
    mands
    1.02
     hace
    1.01
     primeras
    1.01
    ൅
    1.00
     a
    0.99
     souvent
    0.99
    Activations Density 0.225%

    No Known Activations