© 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. 5277
    Prev
    Next
    INDEX
    Explanations

    disciplinary

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

    discipline and rules

    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
     sher
    0.43
     उल
    0.40
    宕
    0.40
     ሽፋ
    0.39
     convoluted
    0.39
    ✾
    0.39
    ContextCompat
    0.38
     sketchbook
    0.38
    豁
    0.38
     Sher
    0.37
    POSITIVE LOGITS
     discipline
    4.81
     Discipline
    4.63
     disciplina
    4.44
    discipline
    4.34
     дисципли
    4.34
     discipl
    4.31
     disipl
    4.25
     Discipl
    4.19
    discipl
    4.06
     disciplines
    3.97
    Activations Density 0.070%

    No Known Activations