© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12517
    Prev
    Next
    INDEX
    Explanations

    Amazon, Brazil, rainforests, AWS clients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barley
    0.49
    崞
    0.47
     Clover
    0.45
     Icelandic
    0.44
     Kabul
    0.44
     Zeeman
    0.44
     Hedgehog
    0.43
    🐹
    0.43
     Carrot
    0.42
    ibald
    0.42
    POSITIVE LOGITS
     Brazil
    1.13
     Amazon
    1.09
     brazil
    1.05
     Brazilian
    1.04
    Brazil
    1.03
    Amazon
    1.02
    巴西
    0.98
    Brazilian
    0.98
     amazon
    0.95
     rainforest
    0.95
    Activations Density 0.063%

    No Known Activations