© 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. 10-GEMMASCOPE-RES-131K
    7. 85637
    Prev
    Next
    INDEX
    Explanations

    giving names to things

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

    This neuron activates on occurrences of the word “name” (i.e. mentions of naming things).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </
    -2.08
    },
    -1.97
     .
    -1.95
     or
    -1.91
     {
    -1.88
     {
    -1.88
    ”,
    -1.84
     (
    -1.80
    」
    -1.79
     to
    -1.76
    POSITIVE LOGITS
    岨
    2.13
    鸶
    1.89
     intelek
    1.88
    憮
    1.86
     keramik
    1.81
     frauen
    1.81
    庒
    1.79
    はコチラ
    1.79
     geolog
    1.72
     conteúdos
    1.70
    Activations Density 0.027%

    No Known Activations