© 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. 4531
    Prev
    Next
    INDEX
    Explanations

    math markup

    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
     negócios
    0.54
     loja
    0.51
    💸
    0.50
    员工
    0.50
     basura
    0.48
    のお店
    0.47
     lojas
    0.47
     کاروبار
    0.47
    偪
    0.46
    Employees
    0.46
    POSITIVE LOGITS
    oles
    0.50
     equation
    0.48
    cl
    0.46
     \
    0.46
     Equation
    0.45
     mathematical
    0.45
     equations
    0.44
     notation
    0.43
    equation
    0.42
     H
    0.42
    Activations Density 0.004%

    No Known Activations