© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14788
    Prev
    Next
    INDEX
    Explanations

    clearing, elimination, and detoxification

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects terms related to biological clearance mechanisms and defense systems that remove pathogens or harmful substances from the body.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is primarily triggered by mentions of biological “clearance” processes (e.g. viral, phagocytic, mucociliary clearance) and related removal of pathogens or molecules.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -1.47
    ¹,
    -1.25
     its
    -1.25
    一样的
    -1.23
    ​,
    -1.22
     similar
    -1.16
     same
    -1.16
    </i>
    -1.15
    ,\\
    -1.14
     ().
    -1.10
    POSITIVE LOGITS
    TAWA
    1.33
    например
    1.25
     şeyler
    1.20
    Borrar
    1.20
    CLUD
    1.18
     prawo
    1.12
     fréquent
    1.12
     amikor
    1.12
     when
    1.11
     freeing
    1.11
    Activations Density 0.160%

    No Known Activations