© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5427
    Prev
    Next
    INDEX
    Explanations

    cleaning and related activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🌉
    0.62
     Coldplay
    0.58
    🌖
    0.56
     Cras
    0.55
     преподава
    0.52
     Diffraction
    0.52
     CUDA
    0.52
    🎷
    0.51
    BSData
    0.49
    ismic
    0.49
    POSITIVE LOGITS
     cleaning
    3.08
    Cleaning
    2.86
     Cleaning
    2.80
    cleaning
    2.80
     cleanliness
    2.63
     limpieza
    2.61
     cleaners
    2.58
     nettoyage
    2.50
     limpeza
    2.50
     cleaned
    2.48
    Activations Density 0.364%

    No Known Activations