© 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. 15405
    Prev
    Next
    INDEX
    Explanations

    Django models

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

    The neuron fires on occurrences of Django model definitions or references to the `models` module (e.g. code declaring or importing Django models).

    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
    ternut
    -2.08
     when
    -2.00
    𓐍
    -1.95
    thodoxy
    -1.92
     with
    -1.90
     in
    -1.84
    柃
    -1.84
    mindedness
    -1.80
     until
    -1.80
     or
    -1.79
    POSITIVE LOGITS
    They
    2.78
    Doesn
    1.94
    The
    1.94
    Nowadays
    1.92
     sogen
    1.84
    .
    1.75
    轻声
    1.73
     toalha
    1.73
     =
    1.70
    Isn
    1.70
    Activations Density 0.003%

    No Known Activations