© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    regulation

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

    regulation and its contexts

    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
     rebirth
    0.41
    利亚
    0.38
    勋
    0.36
     heroes
    0.35
     Hermitian
    0.35
    ពិស
    0.35
     Rashid
    0.35
    捒
    0.35
    Parrocchia
    0.35
     அரி
    0.35
    POSITIVE LOGITS
     regulation
    4.44
     regul
    4.16
    regulation
    4.16
     Regulation
    4.09
     регу
    4.00
    Regulation
    4.00
     regol
    3.97
     Regul
    3.97
     regulación
    3.86
     regulated
    3.81
    Activations Density 0.189%

    No Known Activations