© 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. 84542
    Prev
    Next
    INDEX
    Explanations

    numbers with commas and digits like 5 and 0

    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
    趼
    -1.96
    おわりに
    -1.95
    ↑↑↑</
    -1.91
    ྅
    -1.87
    trabajo
    -1.85
    骓
    -1.84
    któ
    -1.83
    疳
    -1.82
    spodnie
    -1.80
    bezpiecz
    -1.79
    POSITIVE LOGITS
    ..........
    1.96
    .,
    1.90
    の
    1.86
    6
    1.84
    ],
    1.84
     
    1.82
    ...........
    1.82
    rítica
    1.81
     was
    1.78
    1
    1.76
    Activations Density 0.003%

    No Known Activations