© 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. 130966
    Prev
    Next
    INDEX
    Explanations

    grading scale or graded rings

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

    The neuron fires on occurrences of the word “grading,” especially in contexts referring to grading systems or scales.

    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
    嫆
    -2.77
    IANGLES
    -2.67
     Absolutely
    -2.48
    很是
    -2.48
     Lately
    -2.44
    ctose
    -2.39
    
    -2.39
    蓠
    -2.34
     Undoubtedly
    -2.34
     What
    -2.34
    POSITIVE LOGITS
    猡
    2.80
    蚡
    2.75
    </strong>
    2.72
    釭
    2.72
    觏
    2.50
    蟊
    2.50
    ⃚
    2.47
    螄
    2.41
    ";
    2.38
    繻
    2.36
    Activations Density 0.002%

    No Known Activations