© 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. 118128
    Prev
    Next
    INDEX
    Explanations

    Spanish academic or official documents

    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
    verbindung
    -0.89
     atento
    -0.79
     Wyndham
    -0.78
     leuke
    -0.78
     representado
    -0.76
     Zachary
    -0.76
    cambios
    -0.75
     ejecut
    -0.74
    万物
    -0.74
    Pov
    -0.72
    POSITIVE LOGITS
     попере
    0.81
    
    0.79
    eavour
    0.79
    enosti
    0.75
    台中
    0.74
     comigo
    0.72
     Palestina
    0.71
     Pied
    0.70
    Spanish
    0.70
     belonged
    0.70
    Activations Density 0.020%

    No Known Activations