© 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. 34-GEMMASCOPE-RES-131K
    7. 32832
    Prev
    Next
    INDEX
    Explanations

    medical research guidelines and standards

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

    references to research methodology guidelines like PRISMA, CONSORT, and Cochrane in academic literature.

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

    The neuron fires strongly on numeric tokens (e.g., reference numbers, years, counts) in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Så
    -0.79
    Matt
    -0.79
     дипло
    -0.78
    ooker
    -0.76
    Monthly
    -0.76
     Hetero
    -0.75
     mapStateToProps
    -0.75
    اگر
    -0.75
     program
    -0.74
    Cloud
    -0.74
    POSITIVE LOGITS
     ethical
    1.00
     trials
    0.96
     WMA
    0.95
     Trials
    0.95
     Declaration
    0.94
     Ethical
    0.94
     CONS
    0.92
    trials
    0.87
    declaration
    0.84
     declaration
    0.84
    Activations Density 0.071%

    No Known Activations