© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15250
    Prev
    Next
    INDEX
    Explanations

    dust

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    瘀
    0.66
    泄
    0.61
    流水
    0.59
     effluent
    0.59
    اوار
    0.58
     plumber
    0.57
     Wastewater
    0.57
     urine
    0.57
     sludge
    0.57
    展
    0.57
    POSITIVE LOGITS
    dust
    1.21
    Dust
    1.20
     dust
    1.20
     dusted
    1.15
     Dust
    1.13
     bunnies
    1.03
     dusting
    0.97
    particles
    0.95
     Dustin
    0.94
    尘
    0.94
    Activations Density 0.019%

    No Known Activations