© 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. 9673
    Prev
    Next
    INDEX
    Explanations

    equations to solve

    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
    }
    -2.33
    ’
    -2.00
    </h1>
    -1.80
    k
    -1.79
    ou
    -1.70
     neuer
    -1.68
    {
    -1.66
     
    -1.63
    ,
    -1.63
    ó
    -1.63
    POSITIVE LOGITS
    elesaikan
    2.13
    𓋼
    1.84
     bekämp
    1.76
     anpassen
    1.75
     schlafen
    1.74
    るのは
    1.67
     navide
    1.65
     fédé
    1.63
    
    1.63
    槤
    1.62
    Activations Density 0.033%

    No Known Activations