© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74758
    Prev
    Next
    INDEX
    Explanations

    german language fragments

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

    The neuron fires strongly on non-English (chiefly Germanic) word fragments—i.e. tokens coming from German, Danish, Swedish, Norwegian, etc.—so it’s basically detecting foreign-language text.

    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
    s
    -2.38
    -2.11
     beeinf
    -2.09
    ânia
    -2.08
     bedeckt
    -2.05
    klaim
    -2.03
     teilweise
    -1.99
    -1.98
     exciting
    -1.97
    providedIn
    -1.95
    POSITIVE LOGITS
     जब
    2.20
     cuando
    1.89
     carrot
    1.88
     handker
    1.86
    
    1.84
    
    1.84
     ‘’
    1.82
    ⡪
    1.81
    鸸
    1.80
     добавить
    1.78
    Activations Density 0.023%

    No Known Activations