© 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. 128266
    Prev
    Next
    INDEX
    Explanations

    research papers and texts

    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
    氬
    -0.96
     se
    -0.96
     didn
    -0.94
     either
    -0.94
     my
    -0.93
    sikker
    -0.90
     '/';
    -0.88
     desde
    -0.85
    τζ
    -0.84
     us
    -0.84
    POSITIVE LOGITS
     which
    1.27
     where
    1.16
     then
    1.07
     habían
    1.04
     όπου
    1.01
    惋
    0.97
     ausreich
    0.94
    malige
    0.93
     when
    0.93
    Ранее
    0.92
    Activations Density 0.052%

    No Known Activations