© 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. 83132
    Prev
    Next
    INDEX
    Explanations

    XML and code structure

    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
     three
    -1.05
     what
    -0.95
    еры
    -0.93
    *}
    -0.91
     koll
    -0.90
    droj
    -0.89
     Mün
    -0.88
    霏
    -0.87
     for
    -0.86
     want
    -0.86
    POSITIVE LOGITS
    begins
    0.99
     spearheaded
    0.93
     idiotic
    0.90
     SIB
    0.88
    開始
    0.88
     commencer
    0.88
     renegade
    0.87
     angu
    0.87
     reo
    0.87
     propelled
    0.87
    Activations Density 0.000%

    No Known Activations