© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104816
    Prev
    Next
    INDEX
    Explanations

    words starting with T

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

    The neuron detects capitalized personal names and initials (e.g. author surnames and name initials).

    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
     помню
    -1.64
     dieser
    -1.56
    胧
    -1.55
    ⿷
    -1.54
     bears
    -1.53
    
    -1.50
    ॲ
    -1.48
    >
    -1.45
     espírito
    -1.42
    avras
    -1.42
    POSITIVE LOGITS
    </h5>
    1.91
    ate
    1.83
    	
    1.66
    </td>
    1.56
    </i>
    1.47
    л
    1.46
    < 
    1.41
    人们
    1.40
    телем
    1.39
    old
    1.37
    Activations Density 0.061%

    No Known Activations