© 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. 65532
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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
     to
    -2.00
    ⟞
    -1.87
     hizo
    -1.79
     çat
    -1.75
     they
    -1.73
     doesnt
    -1.69
    了很多
    -1.66
    最重要
    -1.63
     durumu
    -1.63
    はその
    -1.63
    POSITIVE LOGITS
    oooooooo
    1.80
    2
    1.73
    -.-
    1.65
    ㍑
    1.64
     Mesin
    1.57
     Issus
    1.56
     uye
    1.56
     maillot
    1.55
    吳
    1.55
     Startseite
    1.55
    Activations Density 0.004%

    No Known Activations