© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79299
    Prev
    Next
    INDEX
    Explanations

    words starting with Des

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

    This neuron activates on tokens beginning with the character sequence “des,” catching words or names that start with the prefix “des.”

    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
    ListFragment
    -0.83
     Harsh
    -0.80
    ><!--
    -0.79
     戸
    -0.78
     Everyday
    -0.76
     Frag
    -0.73
    ^{*
    -0.72
     Supplies
    -0.71
    ätzen
    -0.70
    طبيق
    -0.70
    POSITIVE LOGITS
    consider
    0.80
    coupled
    0.79
     trasera
    0.78
    entire
    0.77
    nter
    0.76
    ሲ
    0.76
     入
    0.75
     lascia
    0.75
     accomplish
    0.74
     muốn
    0.74
    Activations Density 0.040%

    No Known Activations