© 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. 15180
    Prev
    Next
    INDEX
    Explanations

    Python url requests and names

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

    The neuron detects occurrences of the Python “urllib” library (e.g. import or attribute references).

    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
     has
    -2.83
    !”
    -2.58
     还
    -2.55
     欣赏
    -2.44
     dislike
    -2.44
     も
    -2.39
     may
    -2.38
     その
    -2.36
     mistakenly
    -2.33
     soñ
    -2.33
    POSITIVE LOGITS
    ’
    4.31
    s
    4.13
    厹
    3.47
    2
    3.23
    o
    3.23
    the
    3.22
    ，
    3.06
    旆
    2.97
    Ꮞ
    2.91
    4
    2.86
    Activations Density 0.042%

    No Known Activations