© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15289
    Prev
    Next
    INDEX
    Explanations

    WhatsApp, chat, messaging

    np_acts-logits-general · gemini-2.5-flash-lite

    end-to-end encrypted chat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    醛
    0.57
    境界層
    0.52
    苅
    0.50
     rDNA
    0.50
    土壤
    0.48
     карбо
    0.48
     ovarian
    0.47
     породы
    0.47
    赭
    0.47
    鉚
    0.47
    POSITIVE LOGITS
     chat
    1.17
     chatting
    1.16
     Whatsapp
    1.16
     WhatsApp
    1.15
     Chat
    1.09
    聊天
    1.05
    WhatsApp
    1.05
    chat
    1.04
    Chat
    1.03
     whatsapp
    1.03
    Activations Density 0.064%

    No Known Activations