© 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. 33467
    Prev
    Next
    INDEX
    Explanations

    code and programming terms "link"

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

    The neuron strongly activates on import paths and tokens related to routing—especially occurrences of “Link” and “router.”

    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
     bilgisayar
    -0.90
    VISIONS
    -0.88
    êmica
    -0.86
     guessed
    -0.85
    Calib
    -0.82
     warszawa
    -0.80
     –
    -0.79
     variations
    -0.79
     Kartoff
    -0.79
     Menggunakan
    -0.79
    POSITIVE LOGITS
    логии
    1.05
    TO
    1.00
    uyasha
    0.99
    ۔۔
    0.97
    "")
    0.96
     themselves
    0.96
    elementType
    0.94
     membuat
    0.93
     jumlah
    0.92
     Dieser
    0.92
    Activations Density 0.001%

    No Known Activations