© 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. 75913
    Prev
    Next
    INDEX
    Explanations

    reverse sequences

    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
     opr
    -0.75
    ägg
    -0.75
    န်
    -0.75
    uang
    -0.73
     acadé
    -0.73
    ByKey
    -0.71
    ické
    -0.69
    owiak
    -0.69
    fontStyle
    -0.68
    Singular
    -0.67
    POSITIVE LOGITS
     reverse
    1.21
     reversed
    1.13
    reversed
    1.10
    Reversed
    0.91
    反
    0.87
    テーション
    0.85
    yx
    0.81
    reverse
    0.80
     odw
    0.79
    Jack
    0.78
    Activations Density 0.048%

    No Known Activations