© 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. 17156
    Prev
    Next
    INDEX
    Explanations

    I have, they did, there is

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

    actually or not

    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
     however
    0.95
    however
    0.91
     tuttavia
    0.84
    Certainly
    0.81
     हालांकि
    0.79
     certainly
    0.79
     azonban
    0.79
     certes
    0.77
     unfortunately
    0.77
     cependant
    0.77
    POSITIVE LOGITS
     entirely
    0.55
    并不是
    0.53
     전혀
    0.52
    竟然
    0.52
    并非
    0.51
    并没有
    0.50
    不仅仅
    0.50
     kostenlos
    0.49
     вовсе
    0.48
    竟
    0.48
    Activations Density 0.225%

    No Known Activations