© 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. 83789
    Prev
    Next
    INDEX
    Explanations

    specifications and standards

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

    The neuron fires on technical specification language describing performance requirements, tolerances, and compliance with engineering standards.

    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
     Simon
    -0.81
     Simons
    -0.79
    Simon
    -0.75
    вала
    -0.74
    適用
    -0.73
    gameOver
    -0.71
    brada
    -0.69
    ContextCompat
    -0.68
    poner
    -0.67
    Tires
    -0.65
    POSITIVE LOGITS
     specifications
    5.91
     specification
    5.25
     specs
    4.81
     Specifications
    4.53
     Specification
    4.28
    specification
    4.25
    specifications
    4.19
    Specifications
    3.89
    Specification
    3.88
    specs
    3.86
    Activations Density 0.081%

    No Known Activations