© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113350
    Prev
    Next
    INDEX
    Explanations

    keyword usage

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

    the word "keyword" or "keywords" in technical or search-related contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects occurrences of the term “keyword.”

    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
    {
    -3.11
    ↵
    -2.61
     It
    -2.47
    ’
    -2.42
    {
    -2.34
     Also
    -2.23
     Now
    -2.22
    }
    -2.20
    其余
    -2.19
     But
    -2.16
    POSITIVE LOGITS
    ྅
    2.70
    獁
    2.50
     复古
    2.36
    炻
    2.25
     để
    2.25
    婓
    2.22
     diskusi
    2.20
    ᭝
    2.20
    Ꮄ
    2.19
    
    2.19
    Activations Density 0.005%

    No Known Activations