© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112558
    Prev
    Next
    INDEX
    Explanations

    service, safety, factors, enhancements

    np_acts-logits-general · gemini-2.5-flash-lite

    medical advice and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getKey
    0.51
    timeInterval
    0.49
    setWidth
    0.48
     гра
    0.47
     экономической
    0.46
    getSelectedItem
    0.46
    景
    0.45
    躊
    0.45
    createElement
    0.45
     ډاونلوډ
    0.45
    POSITIVE LOGITS
    '
    0.60
     enhanced
    0.54
     crystals
    0.54
     increases
    0.53
     whenever
    0.53
     decreases
    0.52
    Whenever
    0.52
     maximizes
    0.52
     aumenta
    0.51
     app
    0.51
    Activations Density 0.001%

    No Known Activations