© 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. 87269
    Prev
    Next
    INDEX
    Explanations

    " software" after comma

    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
    niejszy
    -0.70
    mang
    -0.69
     Reset
    -0.66
     holds
    -0.65
    Uwagi
    -0.65
    menuBar
    -0.65
     Pembroke
    -0.64
     ataca
    -0.64
     reset
    -0.63
    jenkins
    -0.63
    POSITIVE LOGITS
    uzi
    0.77
     infatti
    0.76
     للمعارف
    0.72
    訝
    0.72
    윗
    0.70
     vys
    0.69
    Etymology
    0.69
    combo
    0.69
    comes
    0.68
    omla
    0.68
    Activations Density 0.054%

    No Known Activations