© 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. 60871
    Prev
    Next
    INDEX
    Explanations

    City names and foreign person names

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

    It responds to tokens containing non-standard Unicode characters (e.g. foreign-script letters, diacritics, or emoji).

    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
    '
    -3.52
    ”.
    -2.61
    緜
    -2.47
     ของ
    -2.44
    *
    -2.42
    1
    -2.34
     した
    -2.30
    嫵
    -2.27
    wns
    -2.16
    ’
    -2.14
    POSITIVE LOGITS
    阉
    2.89
    謦
    2.63
    薅
    2.61
     include
    2.56
    ୮
    2.52
    CÓMO
    2.48
    玙
    2.47
     same
    2.42
    
    2.39
    傀
    2.36
    Activations Density 0.012%

    No Known Activations