© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3332
    Prev
    Next
    INDEX
    Explanations

    corporate and political influence

    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
     cheated
    0.78
     Fraud
    0.74
    詐
    0.72
    騙
    0.72
    Fraud
    0.70
     forgery
    0.70
     Theft
    0.69
    欺
    0.68
     frauds
    0.68
     fraudulent
    0.67
    POSITIVE LOGITS
     lobbying
    1.81
    lobby
    1.81
     Lobby
    1.76
     lobby
    1.75
     Influence
    1.67
     lobbyists
    1.66
    Influence
    1.65
    influence
    1.62
     influence
    1.60
     influencia
    1.48
    Activations Density 0.151%

    No Known Activations