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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9990
    Prev
    Next
    INDEX
    Explanations

    purification and separation processes

    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_31_width_262k_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
     سیاسی
    0.55
     полити
    0.53
    承诺
    0.51
     політи
    0.50
    衔
    0.50
     मुहैया
    0.48
     паліты
    0.48
    ედერ
    0.48
    坚定
    0.48
    ᙱ
    0.47
    POSITIVE LOGITS
     extraction
    0.97
     purification
    0.91
     filtration
    0.88
     extracting
    0.88
     separation
    0.85
    extraction
    0.81
     filtrate
    0.80
     purify
    0.80
     extract
    0.79
     extracted
    0.79
    Activations Density 0.074%

    No Known Activations