© 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. 60376
    Prev
    Next
    INDEX
    Explanations

    physical properties of objects

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

    The neuron fires on mentions of sporting‐equipment items (e.g. golf clubs, fly rods, 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
    ڌ
    -0.77
     luke
    -0.76
     prevision
    -0.75
    Guil
    -0.75
    電力
    -0.75
    PVC
    -0.74
     豪
    -0.72
    urgis
    -0.71
     verursacht
    -0.71
     PLC
    -0.71
    POSITIVE LOGITS
     shaft
    1.38
     flex
    1.12
     shafts
    1.08
     Shaft
    1.01
    shaft
    1.00
    Shaft
    0.88
     stiffness
    0.86
    stiff
    0.86
     stiffer
    0.84
     tip
    0.83
    Activations Density 0.005%

    No Known Activations