© 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
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10437
    Prev
    Next
    INDEX
    Explanations

    Bulgarian, Macedonian, English urban development

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

    Bulgarian words with the letter 'ъ'

    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_40_width_16k_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
     erhöhen
    1.13
    ließt
    1.06
    زندگی
    1.05
     terminée
    1.02
    esempio
    1.02
    qualität
    1.01
     dargestellt
    1.01
    Ὑ
    1.00
    öffentlichung
    1.00
    nikiem
    0.99
    POSITIVE LOGITS
     съ
    1.65
     из
    1.56
     въз
    1.54
     и
    1.43
     тър
    1.41
     е
    1.39
     въ
    1.39
     пър
    1.38
     едно
    1.38
     дъл
    1.36
    Activations Density 0.011%

    No Known Activations