© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3968
    Prev
    Next
    INDEX
    Explanations

    Latvian words, phrases, or concepts

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

    Latvian language and diacritics

    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
     божомолдор
    0.60
     نشست
    0.55
     ойноо
    0.54
    Jimbo
    0.52
     жүктөө
    0.52
    ﮔ
    0.50
     уйнау
    0.50
     انگ
    0.50
    メージ
    0.49
     ойной
    0.49
    POSITIVE LOGITS
    ēj
    1.30
     vē
    1.30
     dzī
    1.30
     ī
    1.27
     kā
    1.25
     cilvē
    1.25
     līdz
    1.24
    ē
    1.23
    ā
    1.23
     pār
    1.22
    Activations Density 0.003%

    No Known Activations