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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7516
    Prev
    Next
    INDEX
    Explanations

    song titles

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

    translate languages, summarize text, classroom use

    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
    4
    0.68
    <0xBE>
    0.64
    
    0.57
     ৪
    0.54
    ৪০
    0.54
     forty
    0.53
     ۴
    0.52
    ৪১
    0.52
    ೪
    0.51
    ４
    0.50
    POSITIVE LOGITS
    Hãy
    0.49
     त्यस
    0.45
     harus
    0.45
     nécess
    0.42
     Hinweis
    0.42
     उसके
    0.42
    Từ
    0.42
     Hasil
    0.42
     Hiện
    0.42
     Hvis
    0.42
    Activations Density 0.271%

    No Known Activations