© 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. 48114
    Prev
    Next
    INDEX
    Explanations

    ObjectId and mmol measurements

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

    This neuron fires on numeric concentration measurements—especially values given in “mmol” (e.g. “1 mmol / l”) format.

    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
    
    -2.80
    樒
    -2.58
     angepasst
    -2.47
     horrifying
    -2.41
    簓
    -2.36
    啬
    -2.27
    茈
    -2.25
     .........
    -2.23
    阏
    -2.23
     !!!!
    -2.22
    POSITIVE LOGITS
    s
    3.14
    .
    2.98
     What
    2.86
    </strong>
    2.47
    ↵
    2.36
     While
    2.23
    頃の
    2.19
     FOR
    2.16
     untuk
    2.13
     Though
    2.13
    Activations Density 0.001%

    No Known Activations