© 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. 22-GEMMASCOPE-RES-131K
    7. 39444
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and notation

    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
     verho
    -1.14
     atk
    -0.91
     to
    -0.91
    लब्
    -0.90
     menegaskan
    -0.90
     ambienti
    -0.89
    也知道
    -0.88
    zusch
    -0.88
     رسانی
    -0.87
    国民
    -0.86
    POSITIVE LOGITS
    Izvori
    1.00
     лікування
    0.98
    をご覧ください
    0.97
    ﾚ
    0.97
    NegativeButton
    0.97
     כולל
    0.96
     беремен
    0.94
    の時
    0.93
     committed
    0.93
     zabezpiec
    0.92
    Activations Density 0.001%

    No Known Activations