© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84276
    Prev
    Next
    INDEX
    Explanations

    predicts 't' after line breaks

    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_22/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
     in
    -2.27
    最近は
    -2.06
    今回は
    -2.03
    がありますが
    -1.95
    女優
    -1.94
    
    -1.93
    ?』
    -1.91
     turist
    -1.81
    俳優
    -1.77
     morena
    -1.75
    POSITIVE LOGITS
     and
    2.30
    為に
    2.22
    '
    2.09
    様な
    1.93
    ようで
    1.91
    了很多
    1.87
    olingo
    1.85
    ↵↵
    1.82
    すっ
    1.76
    っているので
    1.75
    Activations Density 0.067%

    No Known Activations