© 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. 22-GEMMASCOPE-RES-131K
    7. 98529
    Prev
    Next
    INDEX
    Explanations

    URLs and names

    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
     Теперь
    -1.11
     then
    -1.09
     سپس
    -1.00
     następnie
    -0.93
     unveils
    -0.91
     概要
    -0.90
     aband
    -0.89
    Hmm
    -0.86
     Había
    -0.86
     unveiling
    -0.86
    POSITIVE LOGITS
     defekt
    0.91
     infek
    0.84
     kontra
    0.84
    sozial
    0.82
    ую
    0.81
     konkur
    0.81
     ザ
    0.79
    ]]>
    0.79
     memen
    0.77
     anak
    0.77
    Activations Density 0.001%

    No Known Activations