© 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. 107626
    Prev
    Next
    INDEX
    Explanations

    congo, democratic republic

    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
     there
    -1.55
     now
    -1.42
     by
    -1.31
     so
    -1.29
     that
    -1.17
     because
    -1.15
     at
    -1.11
     until
    -1.09
     after
    -1.08
     then
    -1.08
    POSITIVE LOGITS
     constante
    1.02
    コン
    1.01
    confirmed
    0.98
     conserver
    0.96
     konsek
    0.96
     consistente
    0.94
     konusunda
    0.92
    consistent
    0.92
     constantes
    0.89
     con
    0.89
    Activations Density 0.020%

    No Known Activations