© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19325
    Prev
    Next
    INDEX
    Explanations

    django `db`, `middleware`, `conf`

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

    This neuron fires on references to the Django framework’s modules—i.e. import statements or tokens beginning with “django.”

    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
     masih
    -2.09
     STILL
    -1.79
     Still
    -1.70
     Of
    -1.69
    งิน
    -1.65
     hoher
    -1.64
     ۹
    -1.63
     feiner
    -1.59
    ).
    -1.59
    了很多
    -1.56
    POSITIVE LOGITS
    .
    2.06
     and
    1.88
     that
    1.80
    翾
    1.65
    </td>
    1.57
     bewust
    1.56
     zwaar
    1.56
    ajte
    1.52
     volledige
    1.51
     verbonden
    1.48
    Activations Density 0.004%

    No Known Activations