© 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. 109190
    Prev
    Next
    INDEX
    Explanations

    dependencies and build configurations

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

    The neuron detects lines in package‐style metadata (e.g. Debian control or include files) where there’s a field name followed by a colon and a value, especially numeric or dependency entries.

    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
     pappa
    -0.84
     заключается
    -0.80
    Null
    -0.79
     Pará
    -0.77
    mobil
    -0.77
     informou
    -0.74
     属性
    -0.72
    maintain
    -0.72
    Sitz
    -0.72
     tulum
    -0.71
    POSITIVE LOGITS
     runtime
    0.99
     optional
    0.92
     test
    0.91
     dev
    0.88
    runtime
    0.87
     กรัม
    0.85
     woven
    0.85
     Woven
    0.82
     розвитку
    0.81
     tes
    0.79
    Activations Density 0.073%

    No Known Activations