© 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. 22-GEMMASCOPE-RES-131K
    7. 65759
    Prev
    Next
    INDEX
    Explanations

    declaring double variables, methods, and types

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

    The neuron fires on numeric literal tokens (e.g. integer or floating-point constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     görüntüleri
    -1.80
    嵛
    -1.73
    喾
    -1.73
     görüntüsü
    -1.70
     bonté
    -1.70
     jangan
    -1.68
    蟜
    -1.68
     gdy
    -1.68
     daar
    -1.63
    想必
    -1.60
    POSITIVE LOGITS
    0
    1.84
    もあって
    1.65
     marseille
    1.57
     sida
    1.57
     prado
    1.56
    т
    1.56
     saba
    1.55
     pepe
    1.53
     alamy
    1.53
     メニュー
    1.52
    Activations Density 0.007%

    No Known Activations