© 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. 34-GEMMASCOPE-RES-131K
    7. 1059
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    ♗
    -1.03
    他们的
    -0.84
    葑
    -0.81
    ゎ
    -0.79
     SAMPLING
    -0.79
     удар
    -0.79
    ähän
    -0.79
     inconveniente
    -0.78
     THEIR
    -0.77
    の商品
    -0.77
    POSITIVE LOGITS
     ox
    0.91
    ומת
    0.76
     общего
    0.76
    Brightness
    0.76
     LUT
    0.74
     [],
    0.74
    mektedir
    0.74
    чу
    0.73
    決め
    0.73
     FIFO
    0.73
    Activations Density 0.000%

    No Known Activations