© 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. 82729
    Prev
    Next
    INDEX
    Explanations

    articles and studies

    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
    antaranya
    -0.93
    vaila
    -0.91
    ilion
    -0.89
    (""));
    -0.85
    gemeins
    -0.83
    isDead
    -0.82
    antium
    -0.80
    یات
    -0.79
     récol
    -0.79
     Huan
    -0.78
    POSITIVE LOGITS
     results
    1.09
     upgrade
    1.00
    走出
    0.86
    results
    0.85
     through
    0.84
    Results
    0.83
     Results
    0.81
     continuously
    0.78
    śmy
    0.77
     대해
    0.77
    Activations Density 0.023%

    No Known Activations