© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1566
    Prev
    Next
    INDEX
    Explanations

    questions starting with auxiliary verbs

    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_22_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
     yeri
    0.66
     whatever
    0.66
    atar
    0.66
    界
    0.65
    rizio
    0.64
    সো
    0.59
     Kada
    0.58
     whichever
    0.57
    requis
    0.57
    ц
    0.56
    POSITIVE LOGITS
     Does
    3.73
    Does
    3.72
     does
    3.50
    does
    3.06
    Did
    2.86
    Are
    2.82
     Did
    2.81
     Are
    2.77
     did
    2.76
     DOES
    2.56
    Activations Density 0.560%

    No Known Activations