© 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. 84699
    Prev
    Next
    INDEX
    Explanations

    as determined or directed

    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
    Nevertheless
    -0.91
    ണം
    -0.90
     couro
    -0.86
    Где
    -0.85
     presunto
    -0.83
    Противо
    -0.81
    
    -0.81
    ましたが
    -0.81
     vidro
    -0.81
    Оста
    -0.80
    POSITIVE LOGITS
     may
    1.23
     determined
    1.20
     deemed
    1.10
    determined
    1.06
     decided
    1.05
     prescribed
    0.98
     deem
    0.94
     Determined
    0.88
     meest
    0.88
    💺
    0.88
    Activations Density 0.023%

    No Known Activations