© 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. 73806
    Prev
    Next
    INDEX
    Explanations

    add, snd, History, Download, End

    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
     Índice
    -1.30
    ！(
    -1.25
     jú
    -1.20
     histó
    -1.20
     fó
    -1.19
     biblia
    -1.17
    autoIncrement
    -1.17
     pás
    -1.16
     tragé
    -1.16
    maler
    -1.16
    POSITIVE LOGITS
     and
    1.51
     nhung
    1.23
    會有
    1.19
    en
    1.12
     genellikle
    1.05
     meteen
    1.04
     EMF
    1.01
    nt
    1.01
    fo
    0.99
    f
    0.98
    Activations Density 0.001%

    No Known Activations