© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38271
    Prev
    Next
    INDEX
    Explanations

    prohibition era context

    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
    Tél
    -0.97
    Accès
    -0.97
    Puissance
    -0.93
     HARRIS
    -0.83
    хъ
    -0.83
    Tarifs
    -0.83
     quarante
    -0.83
    Largeur
    -0.80
    Extrait
    -0.80
    Pratique
    -0.79
    POSITIVE LOGITS
     Prohibition
    2.05
     Depression
    1.80
     Gatsby
    1.71
     Jazz
    1.55
     twenties
    1.55
     prohibition
    1.54
    Depression
    1.52
     spea
    1.48
    Jazz
    1.48
     jazz
    1.47
    Activations Density 0.028%

    No Known Activations