© 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. 10-GEMMASCOPE-RES-131K
    7. 105939
    Prev
    Next
    INDEX
    Explanations

    names and places

    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_10/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
     dictadura
    -2.92
     dreary
    -2.58
    icksburg
    -2.52
     tématu
    -2.47
     greateſt
    -2.45
    鸲
    -2.44
     porque
    -2.44
     forceful
    -2.42
     nicht
    -2.39
     cojín
    -2.36
    POSITIVE LOGITS
     nominally
    2.28
    </i>
    2.09
    ти
    2.09
    ון
    1.95
     ก็
    1.94
    .
    1.91
    ’,
    1.91
    -</
    1.90
    ات
    1.89
     and
    1.88
    Activations Density 0.001%

    No Known Activations