© 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. 65261
    Prev
    Next
    INDEX
    Explanations

    visual studio or award years

    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
    の人生
    -0.88
    बंध
    -0.84
    绀
    -0.82
    niosek
    -0.79
    ேர
    -0.79
     बज
    -0.79
     Lincolnshire
    -0.77
     ename
    -0.76
    colnshire
    -0.76
     foreigners
    -0.76
    POSITIVE LOGITS
    sworth
    0.93
     оба
    0.91
    große
    0.84
     both
    0.84
    viewModel
    0.81
     Larger
    0.81
    çi
    0.79
    .',
    0.78
     cả
    0.77
    …»
    0.77
    Activations Density 0.135%

    No Known Activations