© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63469
    Prev
    Next
    INDEX
    Explanations

    official greetings or ceremonies

    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
    VERTICAL
    -0.95
    циали
    -0.95
    biol
    -0.92
    sendRedirect
    -0.90
    dulos
    -0.90
     Helpful
    -0.88
    اية
    -0.88
    bolista
    -0.87
     古着
    -0.85
    邮箱
    -0.84
    POSITIVE LOGITS
     protocol
    1.61
     dignitaries
    1.60
     ceremonial
    1.51
     VIP
    1.31
     greeting
    1.30
     dign
    1.23
     protocols
    1.19
     official
    1.18
     pomp
    1.18
    protocol
    1.16
    Activations Density 0.041%

    No Known Activations