© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1707
    Prev
    Next
    INDEX
    Explanations

    php code

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

    html documents

    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
    跗
    0.42
    𝖐
    0.40
     इनवर्स
    0.39
    拡散方程式
    0.38
    ણ
    0.38
     फ्रैक्शन
    0.38
    鰯
    0.38
    銠
    0.38
    
    0.38
    Ꮈ
    0.38
    POSITIVE LOGITS
    namespace
    0.83
    php
    0.76
     echo
    0.73
    echo
    0.72
     namespace
    0.67
     php
    0.59
    defined
    0.58
    if
    0.57
    declare
    0.57
    session
    0.56
    Activations Density 0.007%

    No Known Activations