© 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. 67969
    Prev
    Next
    INDEX
    Explanations

    Slavic and Tamil script fragments

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

    The neuron fires on foreign-language tokens (non-English words), detecting words from other languages.

    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
    ’
    -2.44
    '
    -1.95
    
    -1.90
    ↵↵
    -1.88
    en
    -1.80
    2
    -1.80
     Meldung
    -1.79
    
    -1.77
     recibiendo
    -1.73
     Automó
    -1.73
    POSITIVE LOGITS
    ︲
    3.09
     of
    2.34
    p
    2.33
    鋮
    2.30
    ஂ
    2.30
    摃
    2.30
     –
    2.25
    臯
    2.22
    t
    2.22
    ikusbot
    2.20
    Activations Density 0.009%

    No Known Activations