© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53296
    Prev
    Next
    INDEX
    Explanations

    billionaires and businessmen

    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_31_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
     Faculty
    0.53
     Teacher
    0.49
     Nurse
    0.48
     Yoga
    0.47
     Geometry
    0.47
     LaTeX
    0.47
     eviden
    0.47
    嬷
    0.47
     regression
    0.46
     Classroom
    0.46
    POSITIVE LOGITS
     billionaire
    1.43
     businessman
    1.28
     billionaires
    1.27
    businessman
    1.20
     businessmen
    1.20
     tycoon
    1.17
     philanthropist
    1.16
     empresarios
    1.15
     empresario
    1.14
    Businessman
    1.13
    Activations Density 0.095%

    No Known Activations