© 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. 72099
    Prev
    Next
    INDEX
    Explanations

    http and https links

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

    The neuron fires on URL-related fields—e.g. the keys “homepage,” “url,” “repository,” and their surrounding quotes marking web addresses.

    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
     таких
    -0.94
     AUSSI
    -0.92
     fein
    -0.87
     địch
    -0.86
    subplots
    -0.85
    utivos
    -0.84
     other
    -0.83
     với
    -0.83
     dagens
    -0.83
     みた
    -0.82
    POSITIVE LOGITS
     http
    2.58
     https
    2.56
    http
    2.50
    https
    2.38
     www
    1.87
    www
    1.61
    ://
    1.31
    Https
    1.27
    Médaille
    1.07
    unjungi
    1.05
    Activations Density 0.175%

    No Known Activations