© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67511
    Prev
    Next
    INDEX
    Explanations

    res/

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

    This neuron detects the “res” segment in Android XML namespace URIs (the “…/apk/res/…” resource path).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     möjligt
    -1.55
    Señor
    -1.48
    ’
    -1.41
    こんばん
    -1.39
     provocado
    -1.39
    くんの
    -1.38
    Här
    -1.38
    你可以
    -1.37
    schon
    -1.37
    تي
    -1.35
    POSITIVE LOGITS
     its
    2.23
    了他
    1.70
    的吧
    1.57
     gemeinsame
    1.55
    糨
    1.55
     way
    1.52
     discussion
    1.49
    了吧
    1.48
    麽
    1.47
    を搭載
    1.45
    Activations Density 0.001%

    No Known Activations