© 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. 17025
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    numbers and measurement units

    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
    icca
    0.41
     化
    0.38
    soe
    0.38
    르게
    0.36
     Boyd
    0.36
    عى
    0.36
     Kon
    0.35
    rau
    0.35
    ასი
    0.35
     Jij
    0.35
    POSITIVE LOGITS
    壹百
    0.50
     One
    0.45
     ஆயிர
    0.44
    壹
    0.41
     hundred
    0.40
     หนึ่ง
    0.40
     ciento
    0.40
    One
    0.39
     هزار
    0.39
    accurate
    0.39
    Activations Density 0.042%

    No Known Activations