© 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. 8667
    Prev
    Next
    INDEX
    Explanations

    unquestionably furthermore

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

    Arxiv and model

    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
    yó
    0.48
     fác
    0.43
    〇
    0.43
     □
    0.42
    黯
    0.42
    一时
    0.41
     —¿
    0.40
     λό
    0.39
    여
    0.39
    '],
    0.39
    POSITIVE LOGITS
     moreover
    0.82
     unquestionably
    0.67
     furthermore
    0.66
    Moreover
    0.54
     marvelous
    0.54
     Moreover
    0.51
     genuinely
    0.50
    
    0.48
     Furthermore
    0.47
    Furthermore
    0.46
    Activations Density 0.317%

    No Known Activations