© 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. 17910
    Prev
    Next
    INDEX
    Explanations

    Arabic roots and Saint Croix

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

    Arabic, Dust, ortho

    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
    acional
    0.43
    aper
    0.42
    ينات
    0.42
    اوم
    0.42
    abar
    0.41
    賣
    0.41
    achte
    0.40
    peed
    0.40
    താ
    0.40
    岡
    0.40
    POSITIVE LOGITS
     Hosting
    0.44
    orr
    0.40
    Hosting
    0.40
    ضاف
    0.40
     coz
    0.39
     carat
    0.39
    Holland
    0.39
     elb
    0.38
    hosted
    0.38
     hosted
    0.38
    Activations Density 0.000%

    No Known Activations