© 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. 45645
    Prev
    Next
    INDEX
    Explanations

    Rudolph, Q:, Introduction, Tuning

    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
     there
    -0.94
    ējās
    -0.84
    ://
    -0.79
     first
    -0.78
    ٹر
    -0.77
     it
    -0.76
    Ђ
    -0.75
     According
    -0.74
    WithFormat
    -0.73
    喰
    -0.73
    POSITIVE LOGITS
    Ингредиенты
    0.90
    Esti
    0.89
     depiction
    0.89
    Zutaten
    0.89
    DONALD
    0.87
     depict
    0.85
    Cocina
    0.85
    𝑸
    0.85
     ""}
    0.85
    resie
    0.84
    Activations Density 0.000%

    No Known Activations