© 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. 61314
    Prev
    Next
    INDEX
    Explanations

    America and its context

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

    the word “America” (mentions of the country name)

    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
    
    -2.33
    ⑉
    -2.31
    !!!"
    -2.25
    ৢ
    -2.19
    😐
    -2.19
    玙
    -2.16
     hochzeit
    -2.14
     Київ
    -2.11
     manajemen
    -2.09
    tedì
    -2.09
    POSITIVE LOGITS
    .
    3.77
    ↵
    2.92
    饹
    2.30
    ↵↵
    2.28
    {
    2.23
     He
    2.22
    actéristi
    2.19
     "");
    2.19
     The
    2.11
    )-
    2.08
    Activations Density 0.013%

    No Known Activations