© 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. 21023
    Prev
    Next
    INDEX
    Explanations

    artisan vendor publish

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

    The neuron fires on the use of square‐bracket indexing (i.e. “[…]”) in code.

    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
     \
    -2.38
    ()
    -2.31
     But
    -2.17
     \"
    -2.16
    \
    -2.14
     is
    -2.11
     l
    -2.11
     y
    -2.08
    快速的
    -2.08
     {
    -2.06
    POSITIVE LOGITS
    ]['
    3.11
    --"
    2.55
    "?
    2.20
     また
    2.17
    婓
    2.16
    ※※
    2.16
    殽
    2.16
    Often
    2.14
    時の
    2.11
    ]["
    2.09
    Activations Density 0.000%

    No Known Activations