© 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. 59937
    Prev
    Next
    INDEX
    Explanations

    numerical quantities of hundreds

    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
     other
    -2.16
    其他
    -1.67
     anderen
    -1.63
     ungkap
    -1.55
     или
    -1.53
    ",
    -1.52
    莅
    -1.48
    Even
    -1.45
    dijual
    -1.44
     dismay
    -1.43
    POSITIVE LOGITS
    kę
    1.54
     tenemos
    1.54
     tevens
    1.38
    rália
    1.38
     !!!!!
    1.38
     Chré
    1.35
    hpur
    1.34
    ⅝
    1.34
    酵
    1.34
        
    1.33
    Activations Density 0.145%

    No Known Activations