© 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. 127280
    Prev
    Next
    INDEX
    Explanations

    making judgement or decisions

    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
     was
    -2.70
    鱚
    -2.61
    簟
    -2.61
    
    -2.50
    鬭
    -2.42
     馆
    -2.38
     menangis
    -2.38
    盌
    -2.28
     включая
    -2.27
     置物
    -2.27
    POSITIVE LOGITS
    .
    3.80
    
    2.80
    ↵
    2.69
    倘
    2.63
    此外
    2.59
    the
    2.55
     of
    2.45
    ?
    2.44
    除此之外
    2.36
    但是在
    2.34
    Activations Density 0.002%

    No Known Activations