© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26533
    Prev
    Next
    INDEX
    Explanations

    ui component code syntax

    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
     znajdu
    -1.01
     Glaub
    -0.94
    paraíso
    -0.89
     tewas
    -0.84
     个性
    -0.84
     издели
    -0.84
    herbe
    -0.82
     vaiz
    -0.82
     from
    -0.82
    議会
    -0.82
    POSITIVE LOGITS
     silueta
    1.02
     linge
    1.02
     سایر
    1.02
     ANTONIO
    1.02
     紅
    0.98
    ść
    0.97
    acknowled
    0.94
     februari
    0.94
     ceremonia
    0.93
     aras
    0.93
    Activations Density 0.008%

    No Known Activations