© 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. 7702
    Prev
    Next
    INDEX
    Explanations

    Michigan State, Oklahoma State

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

    programming code snippets

    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
    dostęp
    0.43
    邡
    0.35
     свой
    0.35
    िक्स
    0.35
     meskipun
    0.33
    க்ஸாண்ட
    0.33
     นี้
    0.33
    গ্রস্থ
    0.33
    Escolh
    0.32
    ロジー
    0.32
    POSITIVE LOGITS
    及其
    0.81
    とその
    0.58
    及
    0.49
    (-
    0.49
    および
    0.49
    及び
    0.46
     beserta
    0.45
     \&
    0.42
     तथा
    0.42
    <start_of_image>
    0.41
    Activations Density 0.184%

    No Known Activations