© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65485
    Prev
    Next
    INDEX
    Explanations

    generating programming interface constraints

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

    The neuron detects the syntax of generic‐type constraints (e.g. the “where T : …” clauses and associated colons) 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
     senere
    -1.73
    \
    -1.59
    ,
    -1.46
    _
    -1.41
     nôtre
    -1.41
     THEY
    -1.38
     bús
    -1.38
     bym
    -1.32
    ]$
    -1.30
    hline
    -1.30
    POSITIVE LOGITS
    Already
    1.56
    batik
    1.44
     wichtigen
    1.44
     pertama
    1.41
     erlä
    1.39
     heretics
    1.39
    已经被
    1.38
    已經
    1.38
     besonderen
    1.35
     already
    1.34
    Activations Density 0.006%

    No Known Activations