© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38805
    Prev
    Next
    INDEX
    Explanations

    common compound terms

    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
    któ
    -1.34
     修理
    -1.26
     temperaturas
    -1.24
     hırka
    -1.23
     mikä
    -1.18
    ētu
    -1.17
     meleg
    -1.16
    Inggris
    -1.16
    ivez
    -1.15
    元的
    -1.15
    POSITIVE LOGITS
     is
    1.32
    r
    1.20
    le
    1.16
    u
    1.14
     comparação
    1.13
    ī
    1.11
    s
    1.09
    c
    1.09
    ↵↵↵
    1.07
     wichtigsten
    1.07
    Activations Density 0.217%

    No Known Activations