© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    you [verb] / to [verb]

    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
     Learn
    0.59
    োদ্ধ
    0.59
     dred
    0.58
     discover
    0.57
     craters
    0.56
     learn
    0.55
    ヱ
    0.54
     enumerate
    0.54
    ادرات
    0.54
     learns
    0.53
    POSITIVE LOGITS
     view
    0.65
     tolerated
    0.64
     করছিলেন
    0.62
    Charge
    0.62
    VIEW
    0.60
     VIEW
    0.59
    Vision
    0.58
     উঠছে
    0.58
    tolerance
    0.57
    恙
    0.57
    Activations Density 0.160%

    No Known Activations