© 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. 82309
    Prev
    Next
    INDEX
    Explanations

    scale, onset, day, generation

    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
    所以在
    -1.00
     вони
    -0.90
    $.
    -0.89
     должны
    -0.88
    :'#
    -0.87
    については
    -0.86
    vány
    -0.86
    ，”
    -0.85
    attamento
    -0.84
     epide
    -0.84
    POSITIVE LOGITS
     behaving
    0.92
     its
    0.90
     Isten
    0.89
     dür
    0.87
    venue
    0.87
     aiment
    0.86
     sounding
    0.86
     paraître
    0.85
    zelf
    0.82
    NID
    0.82
    Activations Density 0.089%

    No Known Activations