© 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. 913
    Prev
    Next
    INDEX
    Explanations

    not suitable

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

    not, don't, no, never

    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
     bijna
    0.49
    슝
    0.47
     almost
    0.45
    Almost
    0.42
     vooral
    0.42
    逐渐
    0.42
     upravo
    0.41
    almost
    0.41
     Almost
    0.41
    לא
    0.40
    POSITIVE LOGITS
     hề
    0.83
     obstante
    0.68
    妨
    0.67
     interfere
    0.64
     anymore
    0.63
     hesitate
    0.62
     ngờ
    0.61
     bothered
    0.61
     bother
    0.60
    льзя
    0.60
    Activations Density 0.132%

    No Known Activations