© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53844
    Prev
    Next
    INDEX
    Explanations

    programmatic resources

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

    The neuron activates strongly on mentions of “resources” and resource‐access calls (e.g. getResources(), R.drawable.*, resource file paths), so it’s detecting references to resource identifiers 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
    Making
    -0.84
     Making
    -0.81
     ingår
    -0.76
     règlement
    -0.74
    Taking
    -0.74
     بل
    -0.71
     présidenti
    -0.71
     Téléchargez
    -0.71
     Einen
    -0.70
    вгения
    -0.69
    POSITIVE LOGITS
    Resources
    1.02
     resources
    1.01
     resourceCulture
    0.98
     Resources
    0.97
    getResources
    0.96
    AsStream
    0.93
    resources
    0.92
     منابع
    0.87
    资源
    0.86
    ResourceManager
    0.84
    Activations Density 0.001%

    No Known Activations