© 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. 3732
    Prev
    Next
    INDEX
    Explanations

    being somewhere

    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
     vêtements
    -1.98
     tatuajes
    -1.94
    ౩
    -1.91
    Ꭳ
    -1.87
     soigneusement
    -1.80
     taką
    -1.79
    嵎
    -1.78
    なんだか
    -1.77
     wszystkie
    -1.77
     calcetines
    -1.76
    POSITIVE LOGITS
     to
    2.61
     by
    2.55
     in
    2.45
     for
    2.38
     as
    2.17
     from
    2.08
     with
    1.92
     Their
    1.84
     despite
    1.78
     via
    1.63
    Activations Density 0.007%

    No Known Activations