© 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. 10-GEMMASCOPE-RES-131K
    7. 101539
    Prev
    Next
    INDEX
    Explanations

    roman numeral III

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

    This neuron detects occurrences of the Roman numeral “III” (the three-I sequence) used in labels, section headings, stage or group designations, etc.

    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
    恫
    -3.00
    的吧
    -2.92
    pecabe
    -2.56
    残酷
    -2.56
    的呢
    -2.55
    窠
    -2.50
     gleaming
    -2.50
    猥
    -2.48
     varieties
    -2.44
     weary
    -2.42
    POSITIVE LOGITS
     lakini
    2.72
    
    2.38
    ER
    2.38
    匏
    2.33
    ING
    2.31
     industrie
    2.23
    </i>
    2.17
     
    2.16
    獴
    2.13
     påver
    2.11
    Activations Density 0.007%

    No Known Activations