© 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. 10-GEMMASCOPE-RES-131K
    7. 66486
    Prev
    Next
    INDEX
    Explanations

    any thing or any kind

    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
    Possibly
    -1.39
     as
    -1.31
     one
    -1.20
     for
    -1.18
     possibly
    -1.15
    逢
    -1.14
    ươ
    -1.12
     should
    -1.12
    ностях
    -1.12
    estões
    -1.11
    POSITIVE LOGITS
     wahre
    1.52
     beschäf
    1.47
     beobach
    1.25
     überprü
    1.25
     saída
    1.24
     erzä
    1.22
     unterstüt
    1.18
     reempla
    1.17
     behaup
    1.16
     mencionados
    1.16
    Activations Density 0.070%

    No Known Activations