© 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. 48090
    Prev
    Next
    INDEX
    Explanations

    android layout context

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

    The neuron fires on tokens that come from programming code (especially Android/Java/XML snippets) rather than ordinary prose.

    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
     mélanger
    -0.95
     élev
    -0.93
     Taft
    -0.91
     saveurs
    -0.88
     véritables
    -0.88
     ralenti
    -0.85
     disponibilités
    -0.85
     boucles
    -0.84
    Palestine
    -0.84
     médecin
    -0.82
    POSITIVE LOGITS
     what
    1.02
     m
    0.88
     dip
    0.86
     content
    0.86
     start
    0.82
     alpha
    0.81
     current
    0.80
     from
    0.80
     child
    0.78
     cover
    0.78
    Activations Density 0.009%

    No Known Activations