© 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. 82555
    Prev
    Next
    INDEX
    Explanations

    the followed by specific terms

    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
     både
    -2.00
     mêmes
    -1.69
     pourraient
    -1.63
    
    -1.63
    不仅
    -1.62
     fidé
    -1.61
     critères
    -1.60
     nejen
    -1.59
    
    -1.59
    傒
    -1.59
    POSITIVE LOGITS
     like
    2.73
     associated
    2.64
     resulting
    2.58
     subsequent
    2.52
     subsequently
    2.45
     consequently
    2.27
     it
    2.22
     consequent
    2.19
     corresponding
    2.11
    それを
    2.11
    Activations Density 0.145%

    No Known Activations