© 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. 10-GEMMASCOPE-RES-131K
    7. 110855
    Prev
    Next
    INDEX
    Explanations

    celestial stars or shapes

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

    the neuron detects occurrences of the word “starvation” (and related forms like “starved”).

    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
    ↵
    -2.77
    
    -2.42
    要做
    -2.39
    姽
    -2.28
    knowledge
    -2.28
    眼的
    -2.23
    总是
    -2.14
     одну
    -2.13
     רק
    -2.11
    ܃
    -2.11
    POSITIVE LOGITS
     They
    3.17
     {
    2.88
    er
    2.53
     There
    2.52
     From
    2.48
     спросил
    2.48
     my
    2.39
     What
    2.39
    an
    2.34
     various
    2.34
    Activations Density 0.023%

    No Known Activations