© 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. 83176
    Prev
    Next
    INDEX
    Explanations

    creating, rewriting, retagging, recasting

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

    The neuron activates on words prefixed with “re-” (i.e. tokens beginning with “re” that signal repetition or restoration).

    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
    \
    -1.13
     relieve
    -0.96
    振り返
    -0.95
     restrict
    -0.93
     gerçekten
    -0.93
    évalu
    -0.93
     renovar
    -0.91
     antemano
    -0.91
     little
    -0.91
     невели
    -0.90
    POSITIVE LOGITS
     aya
    1.10
     indietro
    1.00
    一遍
    1.00
     Øst
    0.98
    再
    0.96
    ulier
    0.95
    országban
    0.95
    重新
    0.94
     after
    0.94
     critica
    0.93
    Activations Density 0.138%

    No Known Activations