© 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. 34-GEMMASCOPE-RES-131K
    7. 75892
    Prev
    Next
    INDEX
    Explanations

    section headers and code markers

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

    The neuron strongly responds to programming‐language identifier tokens and keywords—especially Objective-C/Swift class, interface, property, and method names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    谷歌
    -0.71
     ótimo
    -0.69
     Godfrey
    -0.68
    iotensin
    -0.68
    itrile
    -0.67
     الرياض
    -0.66
    除非
    -0.66
     Harg
    -0.66
    nados
    -0.66
    stoffe
    -0.64
    POSITIVE LOGITS
    penas
    0.88
    ಇ
    0.83
    为何
    0.80
     cười
    0.79
    zys
    0.78
     Kartoffeln
    0.74
    мир
    0.73
     истории
    0.73
    Disposable
    0.73
     Gemüse
    0.72
    Activations Density 0.018%

    No Known Activations