© 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. 34-GEMMASCOPE-RES-131K
    7. 58675
    Prev
    Next
    INDEX
    Explanations

    ratio of X to Y

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

    This neuron detects occurrences of the word “ratio,” especially when used in numeric or formulaic expressions.

    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
    })$.
    -0.96
     Thirty
    -0.92
     vanished
    -0.91
    batore
    -0.89
    𓆜
    -0.88
     arranged
    -0.88
    Катего
    -0.87
    assins
    -0.85
     trọn
    -0.85
    かれ
    -0.85
    POSITIVE LOGITS
     between
    1.33
    metric
    1.13
    cination
    1.12
     of
    1.12
    timbangan
    1.04
     Ratios
    1.03
     отношению
    0.98
     ratios
    0.97
    ために
    0.95
     Ratio
    0.95
    Activations Density 0.013%

    No Known Activations