© 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. 84372
    Prev
    Next
    INDEX
    Explanations

    android resource identifiers

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

    This neuron detects the “res” token in Android XML namespace or resource URLs (i.e. the “/res/” segments in schema or resource references).

    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
    ,
    -1.09
    IOException
    -1.06
    MatButtonModule
    -1.02
    ministerium
    -1.01
    MatInputModule
    -0.99
    AFFIRMED
    -0.97
    orie
    -0.93
    =(
    -0.93
    }:{
    -0.93
    '+
    -0.90
    POSITIVE LOGITS
    jeje
    1.08
    aunque
    1.06
    estaba
    0.98
    見えて
    0.97
    Awal
    0.95
    lecte
    0.94
     fapt
    0.92
     récemment
    0.91
    われて
    0.91
     sembla
    0.91
    Activations Density 0.001%

    No Known Activations