© 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. 2944
    Prev
    Next
    INDEX
    Explanations

    abstract specific nouns

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

    defining types of activities

    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
     ভালোভাবে
    0.51
    뤘
    0.51
     जरिए
    0.49
     statunitense
    0.49
    LANGUAGE
    0.46
     ഏറെ
    0.43
     arguably
    0.42
    췄
    0.41
     रुपए
    0.41
     benefitted
    0.41
    POSITIVE LOGITS
     буквально
    0.55
     оружия
    0.54
     -\
    0.51
     именно
    0.51
     permissible
    0.50
     neoplasms
    0.48
     mnog
    0.46
     -
    0.45
    ))).
    0.45
     практически
    0.44
    Activations Density 0.030%

    No Known Activations