© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64136
    Prev
    Next
    INDEX
    Explanations

    ASP.NET MVC serialization

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

    This neuron fires on programming‐style identifiers and literals—especially uppercase code tokens (e.g. attribute names, class/method names, numeric literals) in source or error snippets.

    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
    siapkan
    -1.01
     its
    -0.94
     Bucure
    -0.81
    ньому
    -0.79
     many
    -0.78
     boken
    -0.77
     ostensibly
    -0.77
    $'
    -0.76
     hitam
    -0.75
    Its
    -0.73
    POSITIVE LOGITS
    威胁
    0.97
     MVC
    0.88
     malic
    0.85
    cshtml
    0.85
     ASP
    0.84
    uby
    0.84
    Binder
    0.83
     力
    0.83
     cosmos
    0.82
     Crete
    0.82
    Activations Density 0.002%

    No Known Activations