© 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. 34-GEMMASCOPE-RES-131K
    7. 102404
    Prev
    Next
    INDEX
    Explanations

    Midland, Mid Scotland, Mid-Staffordshire

    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_34/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
    нился
    -0.78
    ancienne
    -0.77
    外国
    -0.76
    índ
    -0.73
    cati
    -0.72
    svet
    -0.72
     ото
    -0.72
    Whole
    -0.71
     ورزشی
    -0.71
    RO
    -0.70
    POSITIVE LOGITS
    ّر
    0.95
    plevel
    0.88
    änden
    0.88
     IMMEDIATE
    0.85
    RESUMEN
    0.84
     surla
    0.84
    CommonModule
    0.78
    beur
    0.75
     intervi
    0.75
    valuable
    0.75
    Activations Density 0.026%

    No Known Activations