© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 488
    Prev
    Next
    INDEX
    Explanations

    power dynamic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    屋さん
    0.59
     최소
    0.57
     왔다
    0.56
     excreted
    0.54
     labile
    0.54
     сухо
    0.53
     ಹೋಗ
    0.53
    録
    0.53
    卖家
    0.53
     оплаты
    0.53
    POSITIVE LOGITS
     alloy
    0.58
    农
    0.55
     construction
    0.52
    Introduce
    0.51
     definition
    0.49
    Declare
    0.49
    Late
    0.49
    Definition
    0.49
    Entire
    0.48
    Defining
    0.48
    Activations Density 0.145%

    No Known Activations