© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147355
    Prev
    Next
    INDEX
    Explanations

    set union

    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_262k_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
    =\{
    0.86
     contradictory
    0.75
    contrad
    0.72
    called
    0.72
     =,
    0.70
    subset
    0.69
    (,
    0.69
    =|
    0.69
    =#
    0.67
    vDash
    0.67
    POSITIVE LOGITS
     union
    1.29
     Union
    1.17
    Union
    1.16
    union
    1.10
    UNION
    1.10
     UNION
    1.05
     unión
    0.93
     unions
    0.93
     Unión
    0.88
     الاتحاد
    0.86
    Activations Density 0.009%

    No Known Activations