© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50333
    Prev
    Next
    INDEX
    Explanations

    filter, filtration, filtered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    蜥
    0.39
    干燥
    0.38
    击
    0.38
    溯
    0.38
     লজ্জ
    0.38
     snakes
    0.37
     Conservatory
    0.37
    UIC
    0.36
    ቶ
    0.36
    ровку
    0.35
    POSITIVE LOGITS
     filtration
    1.91
     filters
    1.88
     filtering
    1.88
     filter
    1.85
     filtr
    1.83
     Filter
    1.80
     филь
    1.79
     Filtering
    1.77
     filtered
    1.77
     फिल्टर
    1.72
    Activations Density 0.047%

    No Known Activations