© 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. 79175
    Prev
    Next
    INDEX
    Explanations

    preparing database queries

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

    The neuron is detecting PHP’s object‐operator (“->”) used for property or method access.

    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
    кус
    -0.76
     dando
    -0.76
     État
    -0.75
     mobilier
    -0.74
     acclaimed
    -0.73
    jot
    -0.73
     Ender
    -0.73
    gelopen
    -0.72
     Interval
    -0.72
    ofern
    -0.71
    POSITIVE LOGITS
     prepare
    1.45
     preparation
    1.44
    prepare
    1.26
     preparing
    1.13
     prepared
    1.08
     przygoto
    1.02
     prepares
    0.98
    準備
    0.94
     preparations
    0.94
    Prepare
    0.94
    Activations Density 0.012%

    No Known Activations