© 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. 8806
    Prev
    Next
    INDEX
    Explanations

    plateau

    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
    archiwizowane
    -2.89
    沕
    -2.72
    
    -2.55
    侂
    -2.50
    
    -2.41
     sostu
    -2.39
     itulah
    -2.38
    闐
    -2.36
     beberapa
    -2.31
    呿
    -2.27
    POSITIVE LOGITS
    '
    3.00
    ing
    2.63
    O
    2.56
    <i>
    2.50
    up
    2.34
    said
    2.22
    特别是
    2.22
    ꜆
    2.16
    暌
    2.16
    </h1>
    2.09
    Activations Density 0.003%

    No Known Activations