© 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. 34-GEMMASCOPE-RES-131K
    4. 60756
    Prev
    Next
    INDEX
    Explanations

    herein research findings

    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
     speziellen
    -0.90
    出来ない
    -0.81
     familières
    -0.80
     campuran
    -0.80
     prévue
    -0.79
     in
    -0.77
    formations
    -0.77
    ˵
    -0.76
     wickedness
    -0.75
     European
    -0.75
    POSITIVE LOGITS
     facile
    1.13
    PENG
    0.94
     casca
    0.91
     ascribed
    0.91
     Kompet
    0.90
     Rektor
    0.89
     predicated
    0.89
     rationally
    0.88
     herein
    0.87
     logica
    0.87
    Activations Density 0.337%

    No Known Activations