© 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. 119617
    Prev
    Next
    INDEX
    Explanations

    wrapped around

    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
    
    -1.45
    Izuku
    -1.41
    躥
    -1.36
     tren
    -1.35
     VIET
    -1.32
    咈
    -1.31
    ⚠️
    -1.30
     而
    -1.29
    飒
    -1.29
     ALLE
    -1.26
    POSITIVE LOGITS
     Prefeitura
    1.73
    橚
    1.63
    𐄙
    1.63
    金
    1.50
     kdo
    1.48
     lanza
    1.47
     TWO
    1.44
     by
    1.43
    THE
    1.41
     senha
    1.41
    Activations Density 0.009%

    No Known Activations