© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33650
    Prev
    Next
    INDEX
    Explanations

    C/C++ includes; imports

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

    The main thing this neuron does is detect Android styled‐attribute and resource‐attribute tokens (e.g. TypedArray, attrs, styleable, obtainStyledAttributes).

    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
     彼女
    -1.04
    PDATE
    -1.02
    Πηγή
    -1.01
     pronti
    -1.00
     届
    -0.99
    IBAction
    -0.99
     anadolu
    -0.99
     Volkes
    -0.98
     cepillo
    -0.97
     becomes
    -0.96
    POSITIVE LOGITS
     thar
    1.09
     элементов
    1.02
     elements
    1.02
    eeper
    1.02
    ederen
    1.01
     finalement
    0.99
    ющего
    0.99
     przez
    0.96
    θούν
    0.96
    catalog
    0.95
    Activations Density 0.006%

    No Known Activations