© 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. 10-GEMMASCOPE-RES-131K
    7. 9332
    Prev
    Next
    INDEX
    Explanations

    inyección

    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_10/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
     "
    -1.98
     
    -1.96
     “
    -1.63
     to
    -1.52
     étaient
    -1.52
    了些
    -1.51
    了一种
    -1.51
    了不少
    -1.50
     était
    -1.50
    button
    -1.50
    POSITIVE LOGITS
     such
    2.11
     ventilación
    1.70
     inyección
    1.66
    hasilkan
    1.61
    jadikan
    1.52
     Nguy
    1.52
     urgencia
    1.52
     titolata
    1.50
     renovación
    1.50
     rotación
    1.49
    Activations Density 0.139%

    No Known Activations