© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5999
    Prev
    Next
    INDEX
    Explanations

    chatbots

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

    The neuron detects mentions of messaging apps and related messaging/application service terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     trusses
    0.55
     বী
    0.55
     drawdown
    0.53
    პერ
    0.53
    PPAR
    0.53
     coatings
    0.52
     truss
    0.51
    📀
    0.51
    HPO
    0.51
    valuer
    0.50
    POSITIVE LOGITS
     chat
    2.23
    聊天
    2.11
     chats
    2.06
     Chat
    2.05
    chat
    2.03
    Chat
    2.00
     채팅
    2.00
     chatting
    1.92
    chats
    1.88
     चैट
    1.87
    Activations Density 0.358%

    No Known Activations