© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5256
    Prev
    Next
    INDEX
    Explanations

    histoire des, pay the, use the

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

    determines languages

    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
    那個
    0.63
    那个
    0.57
    すべて
    0.57
     эту
    0.55
     इनका
    0.55
     आपका
    0.52
    这一切
    0.52
    該
    0.51
    全て
    0.50
     उसका
    0.50
    POSITIVE LOGITS
     các
    2.09
     các
    1.74
     των
    1.73
     mga
    1.66
     Các
    1.63
    Các
    1.62
    các
    1.61
     τῶν
    1.42
     los
    1.40
     degli
    1.29
    Activations Density 0.253%

    No Known Activations