© 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. 26928
    Prev
    Next
    INDEX
    Explanations

    numbers and specific abbreviations

    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
    Faith
    -0.79
    ünst
    -0.78
     sprocket
    -0.75
    맥
    -0.75
    ıyla
    -0.74
     ausser
    -0.73
    炀
    -0.72
    Speaking
    -0.71
     طولانی
    -0.70
     utvik
    -0.70
    POSITIVE LOGITS
    .).
    0.81
    )<
    0.77
    世纪
    0.75
    𝑛
    0.74
    (")");
    0.74
     pueblos
    0.73
    恋人
    0.73
    ệm
    0.73
    tm
    0.73
     député
    0.73
    Activations Density 0.007%

    No Known Activations