© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    government entities

    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
    ড়ের
    0.69
    woofer
    0.68
     पट्टी
    0.67
    ড়ো
    0.67
    ɭ
    0.67
    beding
    0.65
     ferromagnetic
    0.65
     shamp
    0.65
     Encoder
    0.64
    ɻ
    0.64
    POSITIVE LOGITS
     government
    3.41
     Government
    3.10
    Government
    3.08
    government
    2.95
     Ministry
    2.82
    政府
    2.79
     GOVERNMENT
    2.71
     governo
    2.71
     gov
    2.64
     govt
    2.64
    Activations Density 0.538%

    No Known Activations