© 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. 10-GEMMASCOPE-RES-131K
    4. 65372
    Prev
    Next
    INDEX
    Explanations

    dimensions of

    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
    鬭
    -2.95
    甶
    -2.95
    ꜆
    -2.89
    蕷
    -2.78
     aggiunge
    -2.77
     prenotazione
    -2.73
     soste
    -2.70
     estrema
    -2.67
    鐿
    -2.67
     trasparente
    -2.66
    POSITIVE LOGITS
    .
    3.66
    而后
    3.16
    ↵
    3.16
    趼
    2.98
      
    2.94
    ⟞
    2.88
     \
    2.81
    <em>
    2.80
    ”،
    2.72
    ⤥
    2.66
    Activations Density 0.012%

    No Known Activations