© 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. 3862
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "black"

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

    The neuron fires strongly on any occurrence of the word “black” (in any case) or as the “Black” prefix in proper names like BlackBerry, Blackjack, 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
    </h3>
    -3.45
    ↵↵
    -3.20
     
    -2.81
    瑒
    -2.64
      
    -2.64
    莛
    -2.48
         
    -2.42
    </strong>
    -2.38
          
    -2.36
    わけで
    -2.34
    POSITIVE LOGITS
    </b>
    3.30
    婓
    2.75
    轫
    2.72
    或
    2.69
     hvit
    2.66
    heureusement
    2.64
    溲
    2.63
     skak
    2.63
     []
    2.56
    縺
    2.53
    Activations Density 0.020%

    No Known Activations