© 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. 75468
    Prev
    Next
    INDEX
    Explanations

    pink color and names

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

    The neuron activates for occurrences of the word “pink,” especially when it appears as part of a title or name.

    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
    ↵↵
    -3.02
    :
    -2.72
     Of
    -2.63
    '
    -2.59
      
    -2.59
        
    -2.58
    ↵
    -2.56
    <b>
    -2.52
     to
    -2.52
    </b>
    -2.42
    POSITIVE LOGITS
    𐑂
    3.25
    Ꮠ
    2.72
    羕
    2.70
    namentales
    2.67
     邸
    2.66
    ꔹ
    2.66
     australiano
    2.61
    Ꮓ
    2.58
    齶
    2.56
    蟶
    2.56
    Activations Density 0.004%

    No Known Activations