© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86575
    Prev
    Next
    INDEX
    Explanations

    URLs with numbers and 'en'

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

    This neuron fires on URL query‐parameter names (e.g. “hl,” “id,” “link,” etc.).

    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
    -
    -3.13
    Also
    -2.50
    "
    -2.45
    It
    -2.27
    '
    -2.25
    \
    -2.19
    {
    -2.17
    [
    -2.00
    Just
    -1.99
    Those
    -1.96
    POSITIVE LOGITS
    ꝛ
    2.09
    镡
    2.05
    <td>
    2.05
     semua
    2.00
    .”
    1.98
    鰾
    1.98
    哢
    1.97
     medes
    1.92
    tiert
    1.91
    ieR
    1.90
    Activations Density 0.017%

    No Known Activations