© 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. 34-GEMMASCOPE-RES-131K
    7. 109464
    Prev
    Next
    INDEX
    Explanations

    waste and trash

    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_34/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
     anticoag
    -0.77
    ích
    -0.76
     pristine
    -0.74
     fielder
    -0.74
    Дере
    -0.74
    urai
    -0.72
    Theft
    -0.72
    lagten
    -0.71
     Aufs
    -0.71
     Latein
    -0.71
    POSITIVE LOGITS
     waste
    2.97
     trash
    2.97
     garbage
    2.80
     rubbish
    2.31
    trash
    2.03
     déchets
    1.98
     refuse
    1.98
    waste
    1.89
     Trash
    1.83
    garbage
    1.82
    Activations Density 0.040%

    No Known Activations