© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11568
    Prev
    Next
    INDEX
    Explanations

    electrical wiring and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     morphologies
    0.54
     сексуа
    0.50
    ვნ
    0.47
    結晶
    0.47
    晟
    0.47
     Heimat
    0.46
     epistem
    0.46
    욬
    0.46
    รางวัล
    0.46
     Saclay
    0.45
    POSITIVE LOGITS
     wiring
    1.17
     Wiring
    0.99
    Wiring
    0.90
     electrical
    0.85
     wires
    0.82
     वायरिंग
    0.82
    wiring
    0.82
     ignition
    0.78
     circuit
    0.75
    电路
    0.74
    Activations Density 0.043%

    No Known Activations