© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35561
    Prev
    Next
    INDEX
    Explanations

    study periods and medical analysis

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

    numerical values and measurements in scientific and medical research papers.

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

    This neuron detects numeric measurements, counts, or quantitative data (e.g. digits and associated measurement contexts).

    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
     corriger
    -1.07
     Eſ
    -1.02
     เป็น
    -1.00
    肮
    -0.98
    镜头
    -0.98
     .......
    -0.97
     herencia
    -0.96
    ཊ
    -0.95
     .........
    -0.94
    镜子
    -0.94
    POSITIVE LOGITS
     on
    1.38
     measured
    1.30
     both
    1.26
     at
    1.22
     through
    1.21
     test
    1.20
     showed
    1.20
     using
    1.17
     tests
    1.12
     recorded
    1.05
    Activations Density 0.455%

    No Known Activations