© 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. 59655
    Prev
    Next
    INDEX
    Explanations

    section numbers and headings

    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
     outros
    -0.77
    ➋
    -0.76
     other
    -0.74
     השני
    -0.74
    ArrayOf
    -0.74
     další
    -0.72
     نفسها
    -0.71
    ②
    -0.71
     faço
    -0.70
    genuine
    -0.69
    POSITIVE LOGITS
    elter
    0.91
     πρώ
    0.87
     înd
    0.79
    cetto
    0.78
     كت
    0.76
     ஏ
    0.75
     problemlos
    0.75
     Primo
    0.73
     gått
    0.73
     Testament
    0.72
    Activations Density 0.026%

    No Known Activations