© 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. 12424
    Prev
    Next
    INDEX
    Explanations

    Objective-C/Swift interface declarations

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

    The neuron detects Objective-C interface declarations with protocol-conformance lists (i.e. the angle-bracketed “<…>” and commas in an @interface line).

    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
    ]
    -1.65
     their
    -1.63
    Perhaps
    -1.61
    Recently
    -1.54
     Ironically
    -1.52
     Perhaps
    -1.52
    Those
    -1.50
     Interestingly
    -1.50
    蒞
    -1.48
     Those
    -1.47
    POSITIVE LOGITS
     you
    1.52
     chè
    1.46
     Ș
    1.41
    ⏑
    1.41
    ALI
    1.41
     molti
    1.41
    Ș
    1.39
    ᠁
    1.39
     juste
    1.38
     acclaimed
    1.35
    Activations Density 0.008%

    No Known Activations