© 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. 28452
    Prev
    Next
    INDEX
    Explanations

    how something is used or performed

    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
     from
    -1.29
     مختلف
    -1.09
    Wady
    -1.06
     sejumlah
    -1.02
     komfor
    -1.01
     oferty
    -1.01
    essége
    -0.99
    Already
    -0.98
     専用
    -0.97
    rektor
    -0.96
    POSITIVE LOGITS
     used
    1.24
     use
    1.01
     cristi
    0.96
    面に
    0.96
     anot
    0.94
     operating
    0.94
    の方に
    0.94
    nother
    0.94
     Runnable
    0.93
     responsible
    0.93
    Activations Density 0.156%

    No Known Activations