© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76427
    Prev
    Next
    INDEX
    Explanations

    contact by chat or call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ็จ
    -0.83
     Debbie
    -0.71
    rac
    -0.68
     Circus
    -0.68
     spool
    -0.66
    یمت
    -0.65
    orka
    -0.65
     يصل
    -0.65
     ภาพ
    -0.64
     lobster
    -0.64
    POSITIVE LOGITS
     chat
    5.97
    chat
    4.59
     Chat
    4.56
    Chat
    4.44
    CHAT
    3.83
     CHAT
    3.77
     chats
    3.59
    聊天
    3.28
     chatted
    3.06
     chatting
    3.05
    Activations Density 0.052%

    No Known Activations