© 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. 8826
    Prev
    Next
    INDEX
    Explanations

    cylindrical shaped or containing parts

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

    The neuron is looking for the letter‐sequence “yd” (as in “Hyde” or the “yndr” in “cylindrical”) in a token.

    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
    ↵↵
    -3.98
          
    -2.64
    曁
    -2.52
    ….
    -2.47
    m
    -2.44
    -2.38
        
    -2.33
       
    -2.33
     ….
    -2.33
    which
    -2.27
    POSITIVE LOGITS
     твоя
    2.94
    鬭
    2.56
     большие
    2.52
    屺
    2.41
     большая
    2.39
     stavu
    2.34
     wiesz
    2.33
     fragmentos
    2.33
    糌
    2.31
    떳
    2.31
    Activations Density 0.003%

    No Known Activations