© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14882
    Prev
    Next
    INDEX
    Explanations

    international or multi-lingual words

    np_acts-logits-general · gemini-2.5-flash-lite

    how to predict or how entities connect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curved
    0.50
    the
    0.49
    my
    0.49
    nit
    0.49
    IT
    0.48
    different
    0.48
    蒙
    0.48
    synt
    0.46
    US
    0.46
    de
    0.46
    POSITIVE LOGITS
     Actualmente
    0.52
     स्वरों
    0.52
     شورای
    0.50
     Dafür
    0.49
     África
    0.49
    骖
    0.48
     चिकित्सकों
    0.48
     Narrative
    0.47
    ্টন
    0.47
    usuarios
    0.47
    Activations Density 0.000%

    No Known Activations