© 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. 1326
    Prev
    Next
    INDEX
    Explanations

    food delivery pickup leftovers

    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
     turco
    -1.62
    难以
    -1.59
     contento
    -1.57
     involunt
    -1.55
    而去
    -1.53
     навіть
    -1.52
     sū
    -1.51
    鏵
    -1.50
     пев
    -1.50
     —
    -1.50
    POSITIVE LOGITS
     '
    1.85
     calentamiento
    1.59
     Gunakan
    1.56
     or
    1.55
     espectaculares
    1.54
    ﻭ
    1.52
     Pastikan
    1.52
     ONLY
    1.52
    ANIUM
    1.50
     geweldig
    1.50
    Activations Density 0.005%

    No Known Activations