© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10287
    Prev
    Next
    INDEX
    Explanations

    waste and garbage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exa
    0.59
    szlig
    0.59
     विफल
    0.58
    诚信
    0.56
    ༩
    0.56
    INDOW
    0.55
    fordern
    0.55
     príp
    0.55
    registry
    0.54
    فق
    0.54
    POSITIVE LOGITS
     heap
    0.98
     disposal
    0.91
     Disposal
    0.89
     Heap
    0.88
     piles
    0.87
    Heap
    0.84
     garbage
    0.83
     waste
    0.80
     pile
    0.80
    廢
    0.80
    Activations Density 0.204%

    No Known Activations