© 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. 886
    Prev
    Next
    INDEX
    Explanations

    Filed and strictly global

    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
     came
    -1.90
     their
    -1.88
     took
    -1.84
     Also
    -1.80
    と思いました
    -1.78
     create
    -1.78
    ～♪
    -1.78
     became
    -1.77
     gave
    -1.68
    していますが
    -1.68
    POSITIVE LOGITS
    
    2.05
     délais
    1.89
     intermin
    1.76
    relatively
    1.74
     Spanyol
    1.72
     概要
    1.72
     Karakter
    1.68
     gewi
    1.66
     kategori
    1.64
    Atm
    1.63
    Activations Density 0.006%

    No Known Activations