© 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. 34-GEMMASCOPE-RES-131K
    7. 102401
    Prev
    Next
    INDEX
    Explanations

    android drawables and appcompat

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find numeric tokens (multi‐digit numbers) in code or resource files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     punggung
    -0.80
     Phòng
    -0.77
    Elemento
    -0.77
     TÉ
    -0.75
    マト
    -0.75
     APPLY
    -0.74
    ゐ
    -0.73
     Hemos
    -0.73
     IMPER
    -0.73
    tagens
    -0.73
    POSITIVE LOGITS
     adjust
    0.81
     Often
    0.80
     often
    0.77
     Mr
    0.75
    га
    0.74
     souvent
    0.74
     Plus
    0.74
     Filho
    0.74
     очень
    0.73
    喱
    0.73
    Activations Density 0.001%

    No Known Activations