© 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. 66958
    Prev
    Next
    INDEX
    Explanations

    assembly attributes, C# code

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

    This neuron detects numeric literals (numbers) in code or metadata contexts.

    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
     andere
    -1.71
     anunciado
    -1.47
     refrigerador
    -1.41
     reciclado
    -1.40
     primeiros
    -1.40
    合适
    -1.37
     encantan
    -1.36
     parques
    -1.35
    ンドウ
    -1.35
     tocado
    -1.34
    POSITIVE LOGITS
    8
    1.80
    4
    1.63
    Apparently
    1.51
     neuesten
    1.50
    是啊
    1.49
     jedynie
    1.48
     undoubted
    1.48
    “
    1.47
    Probably
    1.46
    Compared
    1.44
    Activations Density 0.004%

    No Known Activations