© 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. 3237
    Prev
    Next
    INDEX
    Explanations

    principal component analysis

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

    principal component analysis

    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
     cooperating
    0.43
     сотрудни
    0.43
    ität
    0.39
    ルド
    0.39
     ansi
    0.38
     nasa
    0.38
    とう
    0.38
    ()<
    0.38
    Parks
    0.38
     createArticle
    0.38
    POSITIVE LOGITS
     Hound
    0.41
     Stranger
    0.39
    rock
    0.38
    角度
    0.38
    تيب
    0.38
     الخدم
    0.37
    Trajectory
    0.37
     Tips
    0.37
     ":"
    0.37
     Prejudice
    0.37
    Activations Density 0.000%

    No Known Activations