© 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. 81465
    Prev
    Next
    INDEX
    Explanations

    software development and web technologies

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

    The neuron detects capitalized code identifiers (especially .NET/ASP-NET class or namespace 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
     Tha
    -0.84
    ⇄
    -0.74
    Tha
    -0.73
    OC
    -0.72
    ira
    -0.71
     ebbe
    -0.71
    deles
    -0.71
     $^{
    -0.70
     tha
    -0.69
    atorias
    -0.69
    POSITIVE LOGITS
    Ɍ
    0.83
    Presenters
    0.79
    appoint
    0.78
    CSRF
    0.77
    araan
    0.77
    makeatletter
    0.76
    Aristotle
    0.75
    Continuar
    0.75
    rasp
    0.75
     zapal
    0.74
    Activations Density 0.004%

    No Known Activations