© 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. 81026
    Prev
    Next
    INDEX
    Explanations

    German given names and surnames

    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
     Helden
    -0.90
     Aufen
    -0.89
     Speicher
    -0.85
     Zitron
    -0.85
     Fieber
    -0.81
     Brunnen
    -0.80
     Orten
    -0.80
     Frühl
    -0.79
     Bür
    -0.79
     Katze
    -0.78
    POSITIVE LOGITS
     Busch
    0.85
    Busch
    0.85
     Unterstützung
    0.83
     Pab
    0.82
     Jue
    0.82
     Preisen
    0.82
     Mueller
    0.81
     Schwierigkeiten
    0.80
    Кре
    0.80
    ¼
    0.78
    Activations Density 0.048%

    No Known Activations