© 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. 10-GEMMASCOPE-RES-131K
    7. 69825
    Prev
    Next
    INDEX
    Explanations

    interface declarations in code

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

    The neuron activates on occurrences of the Objective-C “@interface” keyword declaring a class or category.

    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
     každ
    -1.89
    Jäh
    -1.85
     pokud
    -1.84
     แต่
    -1.72
    ± 
    -1.72
    ৢ
    -1.71
    就没有
    -1.71
     kurzem
    -1.70
     amenaz
    -1.68
     refugi
    -1.67
    POSITIVE LOGITS
     dasarnya
    1.89
    ться
    1.84
    </sup>
    1.81
    out
    1.80
    When
    1.76
    ere
    1.75
     With
    1.71
     Owing
    1.69
     racconta
    1.67
    提出
    1.66
    Activations Density 0.002%

    No Known Activations