© 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. 104889
    Prev
    Next
    INDEX
    Explanations

    starting sequence and following tokens

    np_acts-logits-general · gemini-2.5-flash-lite

    words or partial words from non-English languages, particularly those with non-Latin scripts or diacritical marks.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     terkait
    -1.94
     самому
    -1.90
     could
    -1.87
     Because
    -1.85
    
    -1.84
    
    -1.83
     would
    -1.77
    ၟ
    -1.77
    》。
    -1.73
    تیجه
    -1.72
    POSITIVE LOGITS
    s
    2.02
    ing
    1.84
    ⮑
    1.77
    originally
    1.74
     mediocre
    1.65
     gekocht
    1.61
    suggest
    1.54
    僦
    1.54
     mantend
    1.51
    [
    1.51
    Activations Density 0.000%

    No Known Activations