© 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. 22-GEMMASCOPE-RES-131K
    7. 39403
    Prev
    Next
    INDEX
    Explanations

    specific entities and concepts

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

    The neuron activates on salient content nouns—single-word topic or theme markers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     neuve
    -1.31
     bekämp
    -1.26
    hibits
    -1.23
     remarqu
    -1.20
     Ак
    -1.20
    клей
    -1.20
     costado
    -1.20
     These
    -1.18
    ubwa
    -1.18
     vás
    -1.16
    POSITIVE LOGITS
     now
    1.24
     and
    1.13
     gentile
    1.06
     выполнить
    1.05
    最近は
    1.05
    jMenuItem
    1.02
    tenham
    0.96
     itself
    0.96
     again
    0.95
    そして
    0.94
    Activations Density 0.016%

    No Known Activations