© 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. 73763
    Prev
    Next
    INDEX
    Explanations

    import package names

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

    The neuron fires on occurrences of fully qualified class or package names (especially Spark/Streaming exceptions) in code stack traces.

    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
    Jet
    -0.81
     Measures
    -0.75
    單
    -0.74
     mỗi
    -0.73
     take
    -0.73
     Painter
    -0.73
    دخ
    -0.73
    Take
    -0.73
    院
    -0.73
     Mutable
    -0.72
    POSITIVE LOGITS
     trà
    0.79
     estn
    0.78
     wn
    0.78
     bluegrass
    0.78
    contained
    0.77
     incluse
    0.77
    opened
    0.77
    ndez
    0.76
     formes
    0.76
    úd
    0.75
    Activations Density 0.022%

    No Known Activations