© 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. 41-GEMMASCOPE-2-RES-262K
    7. 62794
    Prev
    Next
    INDEX
    Explanations

    excretion and removal

    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_all/layer_41_width_262k_l0_big
    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
     resusc
    0.39
     حضور
    0.39
    ضور
    0.39
     droughts
    0.39
     وص
    0.38
     presença
    0.38
     TORT
    0.38
    哮
    0.38
     nutrient
    0.38
     drought
    0.38
    POSITIVE LOGITS
     expulsion
    0.93
     expel
    0.91
     removal
    0.88
     expelled
    0.85
    排出
    0.82
     excreted
    0.80
     Removal
    0.79
    removal
    0.78
     disposal
    0.78
     away
    0.75
    Activations Density 0.004%

    No Known Activations