© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115642
    Prev
    Next
    INDEX
    Explanations

    active engagement and connection

    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
     svol
    -0.94
    フラン
    -0.80
    Reproduced
    -0.80
    gte
    -0.79
    terno
    -0.79
    iales
    -0.78
    Rapid
    -0.77
    jatel
    -0.77
     Endocrinol
    -0.77
    treme
    -0.76
    POSITIVE LOGITS
     connection
    1.06
    connection
    0.96
     active
    0.88
     engagement
    0.88
     initiation
    0.87
     verbinding
    0.84
     connected
    0.82
     актив
    0.81
     Connection
    0.80
     activated
    0.79
    Activations Density 0.020%

    No Known Activations