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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    town names

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

    Kazakhstan and Mongolia named places

    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
    ﻓ
    0.95
     對
    0.92
    𝓻
    0.91
    𝔀
    0.91
    體
    0.88
    𝓹
    0.88
    應該
    0.88
    playerCards
    0.87
    𝓾
    0.87
    寫
    0.86
    POSITIVE LOGITS
     ө
    1.52
     ү
    1.48
     ә
    1.41
     тү
    1.40
     кө
    1.39
     кү
    1.38
     тө
    1.38
     жа
    1.34
     та
    1.31
     Ү
    1.29
    Activations Density 0.001%

    No Known Activations