© 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. 21741
    Prev
    Next
    INDEX
    Explanations

    Russian, Thai, and German identifiers

    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
    蕯
    -2.05
     vittoria
    -1.93
    俱乐
    -1.84
     bellissima
    -1.81
     pauv
    -1.80
     ecran
    -1.79
     lâmpada
    -1.77
     polaire
    -1.77
     peluche
    -1.76
     voleva
    -1.76
    POSITIVE LOGITS
     of
    2.75
     your
    2.34
     you
    2.23
    ikusbot
    2.02
    1.98
    ou
    1.96
    ◳
    1.90
    s
    1.85
    玙
    1.84
    ifies
    1.83
    Activations Density 0.029%
    No Known Activations