© 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. 24019
    Prev
    Next
    INDEX
    Explanations

    seeing and hearing

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

    The neuron strongly activates on the word “see,” especially when it occurs in phrases like “what you see.”

    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
    %).
    -1.53
    蕺
    -1.51
     uniquement
    -1.50
    蛲
    -1.50
    蹀
    -1.48
     chce
    -1.45
     conformément
    -1.45
    螄
    -1.45
    où
    -1.45
    ffiche
    -1.45
    POSITIVE LOGITS
     from
    1.68
     oftentimes
    1.54
    それぞれの
    1.51
     -
    1.49
     by
    1.41
    wyczaj
    1.37
     lepší
    1.36
     innumerable
    1.34
     glauben
    1.31
     apprehensive
    1.31
    Activations Density 0.023%

    No Known Activations