© 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. 22-GEMMASCOPE-RES-131K
    7. 14127
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structure

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

    The neuron fires on references to “children” or “child” node access (e.g. children arrays, getChildNodes loops) in hierarchical or recursive data structures.

    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
     Erfüllung
    -0.91
     Auseinander
    -0.89
     Empfindung
    -0.89
     others
    -0.85
    itor
    -0.85
     rück
    -0.84
    出了一
    -0.82
     politische
    -0.81
     pousada
    -0.81
     pienso
    -0.79
    POSITIVE LOGITS
     szint
    1.15
     também
    1.08
     тоже
    1.03
    同样
    1.00
     ebenfalls
    1.00
     productores
    0.97
     arī
    0.93
    worten
    0.90
     ANOTHER
    0.90
     éviter
    0.88
    Activations Density 0.011%

    No Known Activations