© 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. 10-GEMMASCOPE-RES-131K
    7. 48008
    Prev
    Next
    INDEX
    Explanations

    suspension systems

    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_10/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
    s
    -3.81
    )
    -2.89
    饪
    -2.75
    镦
    -2.67
    تیجه
    -2.56
    謦
    -2.53
    pulseira
    -2.52
     باسلام
    -2.52
    鬭
    -2.52
    䛗
    -2.47
    POSITIVE LOGITS
    ↵
    2.83
    ).
    2.55
    媗
    2.36
    
    2.25
    瞠
    2.25
    
    2.19
    ឵
    2.16
     将
    2.16
    нку
    2.09
     zunächst
    2.06
    Activations Density 0.006%

    No Known Activations