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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7809
    Prev
    Next
    INDEX
    Explanations

    Romanian and Moldovan places

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

    Bucharest and Fight the New Drug

    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
    awah
    0.44
    Milwaukee
    0.41
    ھ
    0.39
    OOL
    0.39
    Chhattisgarh
    0.38
    Minneapolis
    0.38
    ankan
    0.38
     کمار
    0.38
    鱷
    0.38
    pulsewidth
    0.37
    POSITIVE LOGITS
     Romanian
    2.31
     Romania
    2.17
     Bucharest
    2.16
    Romania
    1.84
     Cluj
    1.78
     Bucure
    1.72
     România
    1.71
     Ruman
    1.70
     Moldova
    1.39
     Bă
    1.31
    Activations Density 0.024%

    No Known Activations