© 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. 10-GEMMASCOPE-RES-131K
    7. 42369
    Prev
    Next
    INDEX
    Explanations

    according to numbers

    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_10/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
    tiously
    -1.35
     Projektu
    -1.35
     complément
    -1.26
     manguera
    -1.24
     laikā
    -1.23
    lllllll
    -1.22
    Scape
    -1.21
    选择
    -1.21
    llllll
    -1.20
    umers
    -1.18
    POSITIVE LOGITS
     to
    2.50
     so
    1.67
     on
    1.40
     only
    1.29
     From
    1.24
     like
    1.17
    ;
    1.14
     bude
    1.14
     in
    1.10
    ਗ਼
    1.10
    Activations Density 0.136%

    No Known Activations