© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2952
    Prev
    Next
    INDEX
    Explanations

    software components and configurations

    np_acts-logits-general · gemini-2.5-flash-lite

    configuration and state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    龕
    0.56
    軼
    0.52
    犢
    0.50
    spacePad
    0.49
     givenChar
    0.49
    餾
    0.49
     سینٹی
    0.48
    膣
    0.48
    疾患
    0.48
    恥
    0.48
    POSITIVE LOGITS
     handler
    0.91
     API
    0.89
    Manager
    0.87
    (),
    0.86
     manager
    0.84
    ="..."
    0.84
    ()
    0.82
     plugin
    0.82
    manager
    0.81
     parser
    0.79
    Activations Density 0.553%

    No Known Activations