© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 465
    Prev
    Next
    INDEX
    Explanations

    support for government policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_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
    Countries
    1.03
     orthonormal
    0.96
    Global
    0.94
     skilful
    0.92
     Maths
    0.91
     learnt
    0.91
     inbuilt
    0.90
    🏏
    0.90
    Physics
    0.89
    worlds
    0.89
    POSITIVE LOGITS
     statewide
    2.15
     federal
    1.83
     Medicaid
    1.65
     Statewide
    1.65
     county
    1.65
     federally
    1.63
    federal
    1.51
     counties
    1.43
    county
    1.37
     County
    1.34
    Activations Density 0.738%

    No Known Activations