© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5714
    Prev
    Next
    INDEX
    Explanations

    item sets

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

    product items and descriptions

    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
     salarié
    0.43
     شاعر
    0.39
     제시
    0.38
    గర
    0.38
     समज
    0.38
    ServerSocket
    0.38
    
    0.38
    ниципа
    0.38
     delect
    0.38
    提出
    0.37
    POSITIVE LOGITS
     combo
    0.82
     designed
    0.79
     ($
    0.78
     sets
    0.78
     made
    0.77
     featuring
    0.77
    套装
    0.77
     Combo
    0.74
     set
    0.74
     Set
    0.73
    Activations Density 0.494%

    No Known Activations