© 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-65K
    7. 3658
    Prev
    Next
    INDEX
    Explanations

    powder and dust

    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_65k_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
    currentRow
    0.79
    TreeMap
    0.73
    鳄
    0.72
    醴
    0.72
    iziert
    0.71
     Hugo
    0.70
     Dolphin
    0.69
     टें
    0.68
    歪
    0.68
    墉
    0.67
    POSITIVE LOGITS
     powder
    2.62
     dust
    2.58
     powders
    2.41
     Dust
    2.32
     Powder
    2.29
     powdered
    2.25
    Dust
    2.24
    powder
    2.19
    dust
    2.18
     powdery
    2.17
    Activations Density 0.333%

    No Known Activations