© 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. 36424
    Prev
    Next
    INDEX
    Explanations

    image formats and data types

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

    This neuron detects mentions of the QImage ARGB32 format (e.g. the token sequence “QImage::Format_ARGB32”).

    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
     after
    -1.83
     during
    -1.73
    centerTitle
    -1.68
     new
    -1.67
     before
    -1.66
     it
    -1.65
     relevant
    -1.59
     time
    -1.59
     two
    -1.43
     his
    -1.41
    POSITIVE LOGITS
     Ayam
    1.67
     nabi
    1.58
     warung
    1.57
     bandar
    1.53
     Seni
    1.49
     Jasa
    1.45
    Beantwoorden
    1.45
     DKI
    1.43
     barca
    1.43
     ayat
    1.43
    Activations Density 0.007%

    No Known Activations