© 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. 53-GEMMASCOPE-2-RES-65K
    7. 6286
    Prev
    Next
    INDEX
    Explanations

    armenian, georgian, sinhala, and english

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

    Indic scripts and Armenian

    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
    йдз
    0.99
    зию
    0.93
    рию
    0.91
    Ⲕ
    0.89
    лянчук
    0.89
    ється
    0.88
    лся
    0.87
    Ⲑ
    0.86
    йович
    0.84
    Это
    0.84
    POSITIVE LOGITS
     մ
    0.78
     հ
    0.75
     ան
    0.74
     տ
    0.73
    0.73
     դ
    0.71
     ու
    0.71
     բ
    0.71
     ար
    0.70
     ամ
    0.70
    Activations Density 0.003%

    No Known Activations