© 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. 9774
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
     EDUC
    -0.93
     both
    -0.92
     vieta
    -0.92
    🉐
    -0.91
    蹓
    -0.89
     SEDS
    -0.89
     CHAMBER
    -0.88
     jätte
    -0.88
    Inspir
    -0.87
     konfig
    -0.87
    POSITIVE LOGITS
     LIKE
    0.94
     (
    0.92
    nev
    0.86
    -
    0.80
     Longer
    0.79
    
    0.77
    ,
    0.77
    FileDescriptor
    0.77
    の人は
    0.77
     الشهر
    0.75
    Activations Density 0.091%

    No Known Activations