© 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. 90070
    Prev
    Next
    INDEX
    Explanations

    words starting with con

    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
     checker
    -1.04
    Checking
    -0.98
     Checker
    -0.97
    checker
    -0.93
    Checker
    -0.93
     checking
    -0.92
    checking
    -0.91
    CHECK
    -0.88
     CHECK
    -0.88
    checkin
    -0.85
    POSITIVE LOGITS
     Con
    1.10
     conc
    1.05
    con
    1.00
    Con
    1.00
     konk
    0.85
     Concordia
    0.83
    شناسی
    0.81
     Conc
    0.80
    tedrale
    0.80
     breiten
    0.80
    Activations Density 0.026%

    No Known Activations