© 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. 22-GEMMASCOPE-RES-131K
    7. 67369
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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_22/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
    IPT
    -1.09
    Цитата
    -1.05
     inder
    -1.03
     ベージュ
    -1.03
     着物
    -1.00
     befre
    -0.99
     pubblici
    -0.99
     Lexer
    -0.98
    cych
    -0.97
    blestone
    -0.96
    POSITIVE LOGITS
     would
    0.98
     just
    0.98
     as
    0.91
     last
    0.90
     tiny
    0.89
     when
    0.88
    Hozzáférés
    0.86
     Despite
    0.83
     if
    0.82
     incl
    0.82
    Activations Density 0.058%

    No Known Activations