© 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. 59207
    Prev
    Next
    INDEX
    Explanations

    UI code and rendering

    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
     جميلة
    -0.81
     tratan
    -0.78
     Kab
    -0.75
    atients
    -0.75
     quà
    -0.73
    irea
    -0.73
    ptes
    -0.71
     Energies
    -0.71
     Ep
    -0.70
     Sparta
    -0.70
    POSITIVE LOGITS
    测量
    0.86
    ']):
    0.82
    subscription
    0.79
    中に
    0.77
    цыі
    0.76
    Geometry
    0.75
    ofib
    0.73
    应用
    0.73
    ━━
    0.72
    yorum
    0.72
    Activations Density 0.035%

    No Known Activations