© 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. 10-GEMMASCOPE-RES-131K
    7. 42702
    Prev
    Next
    INDEX
    Explanations

    phrases starting with to or tu

    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
     and
    -2.47
    sudadera
    -2.13
    ↵
    -1.97
    Bisa
    -1.90
     gekocht
    -1.90
    llten
    -1.85
    嚕
    -1.84
     मैं
    -1.84
    如下
    -1.83
     setelan
    -1.80
    POSITIVE LOGITS
    It
    2.83
    The
    2.69
    </h2>
    2.56
    Moreover
    2.39
     .”
    2.38
     captivated
    2.31
    
    2.20
    "—
    2.19
    "> 
    2.16
     brimming
    2.16
    Activations Density 0.002%

    No Known Activations