© 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. 977
    Prev
    Next
    INDEX
    Explanations

    make sure

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

    make sure

    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
    льних
    0.38
     نبدا
    0.38
    schnitt
    0.38
     bibendum
    0.38
    涳
    0.35
    爰
    0.35
    
    0.34
    =(\
    0.34
    惮
    0.34
     ആവശ
    0.34
    POSITIVE LOGITS
     sure
    4.34
    sure
    4.00
     Sure
    3.77
    Sure
    3.72
     SURE
    3.63
     chắc
    2.88
     certeza
    2.75
     zeker
    2.72
     surely
    2.63
     sû
    2.41
    Activations Density 0.266%

    No Known Activations