© 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. 15779
    Prev
    Next
    INDEX
    Explanations

    cards

    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
     endocrine
    0.60
     Endocrinology
    0.59
     अतिक्रमण
    0.57
     endocr
    0.57
    坻
    0.57
     Metabolic
    0.53
    Metering
    0.52
    祎
    0.51
     सब्
    0.51
     ছুটিতে
    0.51
    POSITIVE LOGITS
     cards
    2.38
    Cards
    2.16
     deck
    2.11
     Cards
    2.08
    cards
    2.05
     poker
    2.02
     card
    2.00
     decks
    1.99
     카드
    1.98
    Deck
    1.93
    Activations Density 0.082%

    No Known Activations