© 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. 105504
    Prev
    Next
    INDEX
    Explanations

    the 1950s

    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
    彼が
    -1.63
    ir
    -1.63
    il
    -1.58
    ris
    -1.48
    ka
    -1.48
     españoles
    -1.44
     dergleichen
    -1.43
    nictví
    -1.43
    r
    -1.40
     estatales
    -1.39
    POSITIVE LOGITS
    苤
    1.49
     consegui
    1.49
    
    1.43
     sorteo
    1.37
    ･･･
    1.37
     jogar
    1.36
    〜。
    1.35
     know
    1.34
     From
    1.33
     hoeveel
    1.33
    Activations Density 0.054%

    No Known Activations