© 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. 75533
    Prev
    Next
    INDEX
    Explanations

    a new method

    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
    する場合
    -1.10
    ження
    -1.04
     anunció
    -1.02
    క్క
    -0.97
     innego
    -0.96
     betrek
    -0.95
     bijvoorbeeld
    -0.94
     vervol
    -0.92
     była
    -0.91
     something
    -0.91
    POSITIVE LOGITS
     method
    2.50
     methodology
    2.17
     novel
    2.08
     procedure
    2.00
     방법
    1.84
    方法
    1.80
     strategy
    1.73
     methods
    1.71
     technique
    1.70
     framework
    1.62
    Activations Density 0.515%

    No Known Activations