© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33834
    Prev
    Next
    INDEX
    Explanations

    grades and sorting

    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_34/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
    ucción
    -0.74
    Ih
    -0.73
     Pythagorean
    -0.73
    עוד
    -0.71
    fender
    -0.70
    FFA
    -0.69
     Würde
    -0.69
    ないで
    -0.69
     Jahrgang
    -0.69
     ahh
    -0.68
    POSITIVE LOGITS
     sorting
    1.07
     Sorting
    1.03
    rounding
    0.96
    rounded
    0.96
    Round
    0.92
    round
    0.91
    Sorting
    0.90
     rounding
    0.88
     grading
    0.86
    poor
    0.85
    Activations Density 0.029%

    No Known Activations