© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48317
    Prev
    Next
    INDEX
    Explanations

    cleaning services and supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
     sorted
    0.46
    vpn
    0.43
    sorted
    0.41
    cooled
    0.41
     séparation
    0.40
    ᚗ
    0.38
    pc
    0.38
    Guitar
    0.38
    锉
    0.37
     kald
    0.36
    POSITIVE LOGITS
     cleaning
    1.32
     Cleaning
    1.27
    Cleaning
    1.27
    cleaning
    1.14
     убор
    1.08
     cleaners
    1.04
    掃除
    0.97
     Reinigung
    0.97
     limpieza
    0.94
     limpeza
    0.92
    Activations Density 0.034%

    No Known Activations