© 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. 14903
    Prev
    Next
    INDEX
    Explanations

    ranking numbers

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

    rating / number patterns

    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
    де
    0.39
    ВИ
    0.38
    Примеча
    0.37
    industrial
    0.36
    юр
    0.36
    е
    0.35
    Если
    0.34
    ównie
    0.34
    approximately
    0.34
    ан
    0.34
    POSITIVE LOGITS
     Wor
    0.38
     Tells
    0.36
     F
    0.34
     Gaff
    0.34
     Ex
    0.34
     Not
    0.34
     Patt
    0.34
     YouT
    0.34
     SEQU
    0.34
     Sailors
    0.33
    Activations Density 0.015%

    No Known Activations