© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    Texas A&M University

    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
    شناسی
    0.77
    astico
    0.75
    どの
    0.74
    ++++++++++++++++
    0.72
    わせ
    0.72
    дания
    0.71
    
    0.69
    இவ்வாறு
    0.69
    ------------
    0.68
    чены
    0.68
    POSITIVE LOGITS
     projector
    0.68
     Eggs
    0.67
     Pepper
    0.64
     balón
    0.63
     Hof
    0.63
     billiard
    0.63
    Tooltip
    0.62
     dibujar
    0.62
    บริ
    0.62
     Lamar
    0.62
    Activations Density 0.087%

    No Known Activations