© 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. 91965
    Prev
    Next
    INDEX
    Explanations

    wood construction materials

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

    This neuron responds to unusually long tokens—especially multi-part or hyphenated words (including long proper names and compound terms).

    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
    niu
    -0.77
    苦
    -0.74
     Meiji
    -0.73
     metallurgy
    -0.72
    الغ
    -0.71
     habang
    -0.71
    maría
    -0.71
     ospiti
    -0.71
    бър
    -0.70
     teflon
    -0.69
    POSITIVE LOGITS
     timber
    1.01
     lumber
    0.99
     Glu
    0.98
     wood
    0.97
     dela
    0.90
     Timber
    0.90
     glued
    0.89
     WOOD
    0.88
     glue
    0.88
    大臣
    0.88
    Activations Density 0.015%

    No Known Activations