© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86615
    Prev
    Next
    INDEX
    Explanations

    code comments and snippets

    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
     “
    -2.03
     what
    -1.50
     [
    -1.48
     не
    -1.46
    </h1>
    -1.41
    </sup>
    -1.39
     “[
    -1.38
     
    -1.37
     him
    -1.33
    !”
    -1.33
    POSITIVE LOGITS
     '',
    1.63
    ٹر
    1.60
    estimating
    1.55
     erhältlich
    1.54
    ljeno
    1.45
    
    1.45
    deauna
    1.45
     totalt
    1.44
     StringVar
    1.44
    Ghz
    1.42
    Activations Density 0.018%

    No Known Activations