© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130303
    Prev
    Next
    INDEX
    Explanations

    saw followed by observation

    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
    cress
    -1.49
    自己
    -1.48
     eerste
    -1.36
     ماذا
    -1.35
    datable
    -1.32
     "
    -1.30
    ongs
    -1.28
    mente
    -1.27
    :[]
    -1.27
    tical
    -1.26
    POSITIVE LOGITS
     hues
    1.38
     fondly
    1.37
     boasted
    1.35
     negras
    1.34
     heard
    1.34
    wają
    1.33
    葙
    1.33
    こちらも
    1.32
     recently
    1.30
    Caractéristiques
    1.30
    Activations Density 0.041%

    No Known Activations