© 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. 130908
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on names and acronyms of multimedia or graphics libraries and frameworks (e.g. SDL, SFML, GTK, OpenGL).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    SDL, ML, pygame, game, computer libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     the
    -2.08
     frühen
    -1.70
    </h4>
    -1.68
    You
    -1.63
     \
    -1.59
     如果
    -1.59
     This
    -1.55
     šo
    -1.55
    zeppelin
    -1.55
    ）　
    -1.54
    POSITIVE LOGITS
    缡
    1.97
    
    1.59
    秾
    1.48
    
    1.43
     PIT
    1.42
    ܆
    1.41
    Tierra
    1.41
    emde
    1.39
     manier
    1.39
    但这
    1.38
    Activations Density 0.005%

    No Known Activations