© 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. 84351
    Prev
    Next
    INDEX
    Explanations

    computer, controller, new device

    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
    ;
    -1.56
     ''
    -1.46
     ;
    -1.41
     -
    -1.41
    :
    -1.38
     F
    -1.38
     With
    -1.37
     can
    -1.37
    is
    -1.36
     ,
    -1.34
    POSITIVE LOGITS
     菇
    1.77
     kompati
    1.64
     tênis
    1.59
     obé
    1.56
     rése
    1.55
     klient
    1.51
     fré
    1.48
     复古
    1.48
     türkiye
    1.47
     faſt
    1.45
    Activations Density 0.082%

    No Known Activations