© 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. 102650
    Prev
    Next
    INDEX
    Explanations

    listing sections or descriptions

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

    The neuron fires on tokens that are part of enumerated lists or list‐structure markers (e.g., items and separators in comma-separated lists).

    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
     without
    -1.25
     нашего
    -1.21
     here
    -1.20
     but
    -1.14
     senza
    -1.11
     unsere
    -1.05
    च्या
    -1.05
     enquanto
    -1.05
     vän
    -1.05
     tanpa
    -1.02
    POSITIVE LOGITS
     that
    1.88
     mied
    1.19
    Cuánt
    1.18
    ૪
    1.12
     these
    1.11
     those
    1.10
     наря
    1.09
    tront
    1.09
     TextAppearance
    1.08
    aarrggbb
    1.08
    Activations Density 0.281%

    No Known Activations