© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2217
    Prev
    Next
    INDEX
    Explanations

    common or usual things

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

    common errors and practices

    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
     specifically
    0.41
    本身的
    0.41
    specifically
    0.39
    ===
    0.38
     Specifically
    0.38
    专门
    0.37
    éget
    0.37
    独自の
    0.37
     específicamente
    0.37
    ==="
    0.36
    POSITIVE LOGITS
     practice
    0.84
    做法
    0.83
    alities
    0.80
    practice
    0.80
     fare
    0.79
     everyday
    0.78
     suspects
    0.74
     практика
    0.73
     standard
    0.72
     practise
    0.70
    Activations Density 0.209%

    No Known Activations