© 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. 98140
    Prev
    Next
    INDEX
    Explanations

    any followed by noun

    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
     quelques
    -1.80
     ۱۵
    -1.68
    𓁹
    -1.59
     diversos
    -1.58
     allerlei
    -1.56
     唯美
    -1.55
     alcuni
    -1.52
     殼
    -1.52
    𓆏
    -1.51
     alguns
    -1.48
    POSITIVE LOGITS
     of
    3.70
     sort
    2.72
     kind
    2.72
     other
    2.08
     additional
    1.97
     more
    1.91
     particular
    1.88
     noticeable
    1.87
     significant
    1.84
     substantial
    1.79
    Activations Density 0.048%

    No Known Activations