© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13416
    Prev
    Next
    INDEX
    Explanations

    code comments and licenses

    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
     as
    -1.29
     when
    -1.19
     of
    -1.19
     in
    -1.14
     (
    -1.13
     with
    -1.13
     Japão
    -1.12
     out
    -1.10
     on
    -1.09
     When
    -1.09
    POSITIVE LOGITS
    还会
    1.17
     gestartet
    1.11
     två
    1.09
     geda
    1.08
    celotti
    1.08
     natten
    1.06
     består
    1.05
     conſ
    1.05
    vereign
    1.02
     spectacular
    1.01
    Activations Density 0.029%

    No Known Activations