© 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. 55714
    Prev
    Next
    INDEX
    Explanations

    economic production and markets

    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
     EBITDA
    -0.84
     Lokal
    -0.83
     NDR
    -0.82
    BuildConfig
    -0.80
    Vendors
    -0.80
    腊
    -0.79
     rout
    -0.79
     запро
    -0.78
     خواب
    -0.78
     Oblig
    -0.77
    POSITIVE LOGITS
     households
    1.04
     Produktion
    0.94
     Alltag
    0.92
     government
    0.88
     Market
    0.87
     exportaciones
    0.87
     producido
    0.86
     Abschied
    0.86
     buyer
    0.86
    Market
    0.86
    Activations Density 0.014%

    No Known Activations