© 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. 22-GEMMASCOPE-RES-131K
    7. 66399
    Prev
    Next
    INDEX
    Explanations

    android resource references

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

    The neuron is picking out numeric literal tokens in code (e.g. resource IDs and other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    轍
    -2.17
     in
    -2.14
    atação
    -2.11
    梟
    -2.11
    
    -1.98
    ですので
    -1.98
    astify
    -1.97
    が
    -1.94
     all
    -1.90
    訛
    -1.88
    POSITIVE LOGITS
    ’
    2.41
    艄
    1.97
    為に
    1.87
    ええ
    1.83
    ままで
    1.80
     coû
    1.78
     They
    1.77
     Enables
    1.77
    ちょこ
    1.76
     diminuer
    1.76
    Activations Density 0.001%

    No Known Activations