© 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. 4236
    Prev
    Next
    INDEX
    Explanations

    sentence connectors in diverse languages

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

    sentence ending punctuation

    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
    있다
    0.49
    ের
    0.43
    DZ
    0.42
    입니다
    0.41
     உள்ளது
    0.40
     থাকায়
    0.40
    phony
    0.39
    %")
    0.39
    साठी
    0.39
    났다
    0.39
    POSITIVE LOGITS
     என்பதை
    0.71
     বটে
    0.70
     என்பத
    0.64
     अतः
    0.62
     বলেই
    0.60
     എന്നതാണ്
    0.59
     ಆದರೆ
    0.58
     కానీ
    0.58
     ancak
    0.57
     لیکن
    0.56
    Activations Density 0.003%

    No Known Activations