© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86928
    Prev
    Next
    INDEX
    Explanations

    introduction and questions

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

    The neuron fires on code-style type and component names—especially plugin interfaces and file-format identifiers (e.g. “plugin,” “File,” “Format,” “Sdf,” “IO,” etc.).

    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
    ?_
    -0.79
    въ
    -0.74
    zung
    -0.72
    躬
    -0.72
     Caballero
    -0.72
     teapot
    -0.70
    HomeAsUp
    -0.70
    ธิ
    -0.69
    ليق
    -0.69
    нисти
    -0.68
    POSITIVE LOGITS
     electronically
    0.87
     ctx
    0.79
    ℓ
    0.78
    BorderFactory
    0.77
     vitamina
    0.73
     Pleasure
    0.73
     Brooks
    0.73
    종
    0.72
     '';
    
    0.72
     ecto
    0.71
    Activations Density 0.007%

    No Known Activations