© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1170
    Prev
    Next
    INDEX
    Explanations

    secretly dividing or conflicting messages

    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_40_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
    糈
    0.55
    狨
    0.52
    Methylsulfanyl
    0.51
    篑
    0.50
    牷
    0.50
    糇
    0.49
    营养
    0.49
     Neurog
    0.49
    ↡
    0.48
     Calyce
    0.48
    POSITIVE LOGITS
     telegram
    1.06
     diplomatic
    0.97
     Telegram
    0.87
     cables
    0.84
    telegram
    0.83
     embassy
    0.82
     diplomats
    0.80
     cable
    0.79
     memoranda
    0.78
     Embassy
    0.78
    Activations Density 0.005%

    No Known Activations