© 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. 14312
    Prev
    Next
    INDEX
    Explanations

    prize

    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
     বিলম্ব
    0.57
     backbone
    0.52
    铿
    0.51
     humbled
    0.50
    ഹു
    0.48
     affirmations
    0.48
     সংসদে
    0.48
     reconnaître
    0.48
     নেতাকর্ম
    0.48
    耸
    0.47
    POSITIVE LOGITS
     prize
    4.22
     Prize
    3.94
    prize
    3.83
     prizes
    3.80
     Prizes
    3.63
    Pri
    2.91
    奖
    2.72
     pri
    2.63
     PRI
    2.59
    獎
    2.55
    Activations Density 0.082%

    No Known Activations