© 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. 17691
    Prev
    Next
    INDEX
    Explanations

    Romanian language and academic texts

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

    Romanian language

    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
     সেটি
    0.47
     नॉन
    0.46
     получить
    0.45
     effettuare
    0.44
     काफी
    0.43
     ಸ್ಟ
    0.42
    舴
    0.42
    そうだ
    0.42
    uiden
    0.42
     প্যাকে
    0.42
    POSITIVE LOGITS
     î
    0.53
     siglos
    0.51
     lahir
    0.42
     vred
    0.42
     emancip
    0.41
     stolet
    0.40
     Dom
    0.39
    Infl
    0.39
     sl
    0.39
     Regression
    0.38
    Activations Density 0.001%

    No Known Activations