© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    post

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

    post, POST requests

    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
     স্নে
    0.37
    ्यूशन
    0.35
    㥽
    0.34
    餓
    0.34
    俪
    0.34
    ណ៍
    0.33
    
    0.33
    ាញ
    0.33
    仂
    0.33
     எதிர
    0.32
    POSITIVE LOGITS
     post
    4.69
    post
    4.53
     Post
    4.47
    Post
    4.38
     पोस्ट
    4.19
     пост
    4.06
     POST
    3.98
    POST
    3.97
     পোস্ট
    3.91
    ポスト
    3.84
    Activations Density 0.467%

    No Known Activations