© 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. 54192
    Prev
    Next
    INDEX
    Explanations

    sports and acquisitions

    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
     skulle
    -0.87
     ≈
    -0.87
     seiner
    -0.86
    deaths
    -0.86
     Sega
    -0.84
    
    -0.82
    痉
    -0.82
    iked
    -0.82
     MARIE
    -0.82
    高于
    -0.82
    POSITIVE LOGITS
     LeBron
    1.23
     umy
    0.92
    Ā
    0.91
    cją
    0.90
     世界
    0.89
     Campionato
    0.87
    ріш
    0.86
     PTSD
    0.86
    Aacute
    0.85
     Jason
    0.85
    Activations Density 0.215%

    No Known Activations