© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77067
    Prev
    Next
    INDEX
    Explanations

    bonsai styling

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

    The neuron is triggered by detailed botanical Q&A text describing plant identification and care (e.g., species names, measurements, and growing requirements).

    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
     festen
    -0.81
    伦敦
    -0.77
     舞台
    -0.76
    DESCRIPTION
    -0.76
    劃
    -0.75
    Claim
    -0.74
     mexico
    -0.73
    Heads
    -0.73
     lesión
    -0.73
    -0.73
    POSITIVE LOGITS
     wiring
    0.92
    wiring
    0.88
    wires
    0.88
     bonsai
    0.87
     wire
    0.84
     training
    0.82
     styling
    0.82
     дерев
    0.81
     Wire
    0.80
     styles
    0.80
    Activations Density 0.010%
    No Known Activations