© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38990
    Prev
    Next
    INDEX
    Explanations

    evaluation of scientific experiments

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

    references to experimental or numerical results in academic papers.

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

    This neuron detects sections describing empirical evaluations, i.e. words indicating numerical or experimental testing and results in scientific abstracts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ㌔
    -1.05
    Filmografia
    -1.03
    指定
    -1.03
    𝙈
    -1.01
    渥
    -1.01
    liptical
    -0.97
     была
    -0.97
     negativas
    -0.96
     bahía
    -0.94
    roup
    -0.94
    POSITIVE LOGITS
     test
    1.40
     results
    1.22
    test
    1.20
     testing
    1.14
     prove
    1.07
    🧪
    1.05
     tests
    1.04
     baut
    1.03
    ลอง
    1.02
     poë
    1.02
    Activations Density 0.040%

    No Known Activations