© 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. 86101
    Prev
    Next
    INDEX
    Explanations

    multilingual word endings

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

    The neuron flags tokens containing non-ASCII Latin letters (i.e. accented or language-specific characters).

    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
    躋
    -2.83
    壟
    -2.77
    ⚋
    -2.58
    }
    -2.48
    ꔹ
    -2.47
    ᠂
    -2.33
    飆
    -2.27
    n
    -2.27
    𐍆
    -2.25
     می‌کنند
    -2.16
    POSITIVE LOGITS
     gewähr
    2.03
     tuvimos
    2.02
     läm
    2.02
    
    2.00
    了一个
    1.99
    寕
    1.98
    
    1.97
    灕
    1.92
     estábamos
    1.91
    '
    1.91
    Activations Density 0.090%

    No Known Activations