© 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. 10-GEMMASCOPE-RES-131K
    7. 57592
    Prev
    Next
    INDEX
    Explanations

    relative risk or risk ratio

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

    The neuron activates on occurrences of the abbreviation “RR” (as in relative‐risk references).

    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
    橚
    -3.23
    葙
    -3.22
    ዡ
    -3.06
    ﱠ
    -3.02
    咴
    -2.81
    䛗
    -2.75
    ڧ
    -2.66
    鸸
    -2.63
    渽
    -2.63
    饪
    -2.63
    POSITIVE LOGITS
    k
    2.47
    m
    2.20
    )-
    2.14
    RR
    2.13
     selben
    2.09
     succinct
    2.09
     Placing
    2.09
    er
    2.08
     Primarily
    2.06
    磲
    2.03
    Activations Density 0.003%

    No Known Activations