© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104342
    Prev
    Next
    INDEX
    Explanations

    screening approaches and applications

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

    The neuron activates for "screening" in medical or research contexts, often followed by "for" or "of" when describing diagnostic or research testing processes.

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

    The neuron responds to mentions of “screen” (especially “screening”) in the sense of testing or assay procedures.

    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
     There
    -2.55
    埽
    -2.38
    人们
    -2.31
    艽
    -2.27
     馆
    -2.27
    ៚
    -2.27
    他没有
    -2.22
     办
    -2.22
    鮃
    -2.22
     untapped
    -2.20
    POSITIVE LOGITS
    0
    2.88
     пять
    2.75
     diesem
    2.61
    o
    2.58
     This
    2.55
    部分は
    2.55
    hasilkan
    2.53
     konsep
    2.39
     hermos
    2.36
    a
    2.33
    Activations Density 0.010%

    No Known Activations