© 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. 109214
    Prev
    Next
    INDEX
    Explanations

    file path or configuration settings

    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
    setCancelable
    -0.82
     vode
    -0.79
     Muni
    -0.76
    راع
    -0.76
    ాని
    -0.73
     Aufnahme
    -0.71
     اسب
    -0.71
    estões
    -0.71
     Barran
    -0.69
    ampingi
    -0.69
    POSITIVE LOGITS
    besides
    0.81
     redo
    0.80
    capture
    0.77
     envoyé
    0.75
    の変化
    0.75
     CDC
    0.74
     río
    0.73
     Abstra
    0.73
    んですね
    0.72
    CONTINUED
    0.72
    Activations Density 0.012%

    No Known Activations