© 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. 11921
    Prev
    Next
    INDEX
    Explanations

    assembly metadata

    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
    ré
    -0.71
    гать
    -0.69
    ंब
    -0.69
    лар
    -0.68
    ◥
    -0.66
     butcher
    -0.65
    ladi
    -0.65
    setOn
    -0.64
    ])){
    -0.64
     exists
    -0.64
    POSITIVE LOGITS
    Cruz
    0.74
     internals
    0.70
     penet
    0.70
    eraus
    0.68
    ⮜
    0.68
     anlaş
    0.67
    Legion
    0.66
     παιδιά
    0.65
     Curry
    0.65
    certificate
    0.65
    Activations Density 0.049%

    No Known Activations