© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71343
    Prev
    Next
    INDEX
    Explanations

    play with media and lists

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

    The neuron strongly activates on instances of the word “play” (in various contexts, casing, and as part of filenames or interface labels).

    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
     
    -2.78
     to
    -2.31
     aument
    -2.19
     Their
    -2.17
    ፨
    -2.14
     utilising
    -2.02
     なお
    -1.98
     prompting
    -1.92
    事が
    -1.88
    诹
    -1.87
    POSITIVE LOGITS
    {
    3.06
    了一个
    2.38
     opérés
    2.31
    澌
    2.31
    }_{
    2.25
     européens
    2.23
     magnétique
    2.20
    8
    2.19
    裡的
    2.17
    6
    2.17
    Activations Density 0.011%

    No Known Activations