© 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. 66561
    Prev
    Next
    INDEX
    Explanations

    programming languages and data types

    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
     how
    -1.19
     when
    -1.13
     with
    -1.08
     after
    -1.07
     of
    -0.96
     such
    -0.96
    無し
    -0.95
     naprawdę
    -0.94
     or
    -0.93
     Schwerpunkt
    -0.93
    POSITIVE LOGITS
     kategor
    1.10
    많
    1.09
    個人的には
    1.04
    腟
    1.04
     shou
    1.04
    ሯ
    1.02
    极其
    1.01
    比べると
    1.01
     knowled
    0.98
     demar
    0.98
    Activations Density 0.003%

    No Known Activations