© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13137
    Prev
    Next
    INDEX
    Explanations

    government assistance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     収納
    0.65
     differentiator
    0.65
    剐
    0.64
    squeeze
    0.60
    进攻
    0.60
     નક્
    0.57
    員工
    0.56
    賊
    0.56
     خار
    0.55
    ```{
    0.55
    POSITIVE LOGITS
     Medicaid
    1.48
     eligibility
    1.25
     TAN
    1.20
     SNAP
    1.17
     Eligibility
    1.14
     subsidized
    1.12
     eligible
    1.09
     SSI
    1.08
     USDA
    1.05
     Eligible
    1.05
    Activations Density 0.115%

    No Known Activations