© 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. 3273
    Prev
    Next
    INDEX
    Explanations

    software and programming tools

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

    python code

    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
    segaretro
    0.46
    த்திக்க
    0.44
     न्यूयॉर्क
    0.44
    andering
    0.43
     hickory
    0.42
     BUILDING
    0.42
     cartil
    0.42
    ަ
    0.41
     BLUEN
    0.40
     maxillary
    0.40
    POSITIVE LOGITS
     plugin
    0.88
     Plugin
    0.84
    插件
    0.84
    ®
    0.83
    MyAdmin
    0.79
    ++
    0.76
    Plugin
    0.75
     plugins
    0.75
     SDK
    0.74
    plugin
    0.74
    Activations Density 0.207%

    No Known Activations