© 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. 33804
    Prev
    Next
    INDEX
    Explanations

    convention dictates

    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
    🧛
    -1.04
     constitue
    -1.02
     discut
    -0.97
    　　　　　　　　　　　　　　　　
    -0.97
    represents
    -0.96
     enthou
    -0.95
     éton
    -0.94
    Erreferent
    -0.94
    lernen
    -0.94
    appears
    -0.94
    POSITIVE LOGITS
     dictates
    3.09
     suggests
    2.80
     says
    2.67
     dictate
    2.63
     suggest
    2.58
     tells
    2.31
     indicates
    2.09
     dictated
    1.98
     requires
    1.86
     allows
    1.80
    Activations Density 0.105%

    No Known Activations