© 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. 118581
    Prev
    Next
    INDEX
    Explanations

    company names and entities

    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
    Мар
    -0.98
    इट
    -0.94
     marchés
    -0.89
    Sony
    -0.85
    блі
    -0.84
    colazione
    -0.84
    BART
    -0.83
     wcześ
    -0.82
    Anna
    -0.81
     chaînes
    -0.81
    POSITIVE LOGITS
     према
    0.85
    Frankly
    0.84
     Przed
    0.84
    Parenting
    0.82
     ermöglicht
    0.82
    Transk
    0.81
     Clears
    0.81
    Guards
    0.81
     vigor
    0.80
    φο
    0.80
    Activations Density 0.045%

    No Known Activations