© 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. 1453
    Prev
    Next
    INDEX
    Explanations

    rectangular shapes

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

    The neuron flags occurrences of the adjective “rectangular,” i.e. explicit mentions of rectangular shapes.

    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
    可以
    -3.70
     The
    -2.98
            
    -2.89
     
    -2.69
    人の
    -2.66
     инстру
    -2.61
    因為
    -2.55
    𖣘
    -2.55
     Когда
    -2.55
    {
    -2.52
    POSITIVE LOGITS
    髡
    2.97
    鸶
    2.88
    曏
    2.86
    扞
    2.78
    餽
    2.77
    ⽌
    2.77
    谵
    2.72
    縯
    2.70
    赁
    2.67
    鹂
    2.67
    Activations Density 0.003%

    No Known Activations