© 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. 34-GEMMASCOPE-RES-131K
    4. 92327
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions

    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_34/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
    oczes
    -0.93
    內容
    -0.92
     ilustração
    -0.90
    這樣的
    -0.88
     Diese
    -0.88
    倆
    -0.88
     parceria
    -0.87
     klasa
    -0.85
    ergic
    -0.85
    这样的
    -0.85
    POSITIVE LOGITS
     của
    1.01
     default
    0.97
     relating
    0.96
     principal
    0.96
     associated
    0.89
    américa
    0.89
     predominant
    0.89
     понравилось
    0.88
    =}
    0.88
    ของ
    0.88
    Activations Density 0.033%

    No Known Activations