© 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. 60761
    Prev
    Next
    INDEX
    Explanations

    cooperation with other organizations

    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
     disiplin
    -0.96
    ograft
    -0.94
     sólo
    -0.93
     romantis
    -0.93
     Pada
    -0.92
     potensi
    -0.92
     bakteri
    -0.91
     konsep
    -0.91
     bağlantılar
    -0.89
     individuel
    -0.88
    POSITIVE LOGITS
     diferentes
    0.91
     according
    0.90
     different
    0.86
     lately
    0.86
     today
    0.85
     increase
    0.84
    illotine
    0.84
     analyzes
    0.84
     diferente
    0.83
    jadikan
    0.83
    Activations Density 0.003%

    No Known Activations