© 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. 10-GEMMASCOPE-RES-131K
    4. 75731
    Prev
    Next
    INDEX
    Explanations

    world's followed by superlatives

    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_10/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
     venons
    -2.00
    
    -1.97
    Ꮷ
    -1.96
    dawg
    -1.95
    薷
    -1.95
    😐
    -1.86
    😚
    -1.84
    atellite
    -1.83
     camry
    -1.82
    trooper
    -1.81
    POSITIVE LOGITS
    "
    3.09
    :
    2.59
    )
    2.36
    ,'
    2.33
    /
    2.02
     With
    2.00
     talented
    1.94
    f
    1.93
     people
    1.92
     esteemed
    1.91
    Activations Density 0.011%

    No Known Activations