© 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. 128956
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    The main thing this neuron does is spot pieces of web addresses (URL components and file‐path tokens).

    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
    uluş
    -1.58
     tunik
    -1.45
     بنابراین
    -1.41
    indonesia
    -1.38
    szt
    -1.37
     atractiva
    -1.35
     tidligere
    -1.34
    xymatrix
    -1.34
    icestershire
    -1.34
     nesten
    -1.30
    POSITIVE LOGITS
     by
    1.68
     those
    1.64
     with
    1.45
     different
    1.35
    change
    1.32
     show
    1.27
    everyone
    1.25
     the
    1.24
    different
    1.24
     mesma
    1.21
    Activations Density 0.029%

    No Known Activations