© 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. 41-GEMMASCOPE-2-RES-65K
    7. 13967
    Prev
    Next
    INDEX
    Explanations

    supply

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Cousin
    0.55
    véd
    0.51
    劃
    0.49
     Warrior
    0.47
     рыба
    0.47
    Roberts
    0.46
    illiard
    0.46
    SIS
    0.46
    哳
    0.46
     Dud
    0.45
    POSITIVE LOGITS
     supply
    5.50
     Supply
    5.19
    supply
    5.19
    Supply
    5.16
     SUPPLY
    5.03
     supplies
    4.53
     Supplies
    4.22
     SUPPL
    4.19
     공급
    4.16
    供应
    4.13
    Activations Density 0.259%

    No Known Activations