© 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. 3464
    Prev
    Next
    INDEX
    Explanations

    Armenia, Armenians, Karabakh, Azerbaijan

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

    Armenia 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
     EFFECTS
    0.53
    𝔹
    0.51
    ✼
    0.49
     Everglades
    0.48
     perfeito
    0.47
    𝓂
    0.47
    🦟
    0.47
    𝙄
    0.47
     বিটিআই
    0.46
     perfeita
    0.45
    POSITIVE LOGITS
     Armenian
    2.38
     Armenia
    2.22
     Yerevan
    2.20
     Armenians
    2.03
     Armen
    1.60
     Azerbaijani
    1.50
     Azerbaijan
    1.39
    Azer
    1.30
     Ararat
    1.28
     Karab
    1.23
    Activations Density 0.046%

    No Known Activations