© 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. 130987
    Prev
    Next
    INDEX
    Explanations

    instructions and definitions

    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
     biela
    -2.17
    zdo
    -1.70
     hırka
    -1.66
    wym
    -1.64
    szak
    -1.62
     bicicletas
    -1.61
     favoris
    -1.59
     Popis
    -1.56
    rodz
    -1.54
     temperaturas
    -1.53
    POSITIVE LOGITS
    u
    2.36
    is
    2.14
    b
    2.13
    ar
    2.09
    at
    2.08
    o
    2.06
    in
    2.03
    an
    2.02
    se
    1.97
    d
    1.97
    Activations Density 0.021%

    No Known Activations