© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3468
    Prev
    Next
    INDEX
    Explanations

    wet

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

    energy-oxygen reaction

    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
     MPI
    0.45
     প্রান্ত
    0.43
     Along
    0.41
     हनु
    0.39
    同梱
    0.38
     пон
    0.37
    驍
    0.37
    ləşdirilib
    0.36
     incon
    0.36
     incapacitated
    0.35
    POSITIVE LOGITS
    Wet
    0.73
    wet
    0.68
     wet
    0.66
     Wet
    0.65
     struck
    0.61
     expel
    0.61
     mam
    0.60
    湿
    0.60
    Mam
    0.57
     expelled
    0.57
    Activations Density 0.000%

    No Known Activations