© 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. 41878
    Prev
    Next
    INDEX
    Explanations

    unpacking or spreading arguments

    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
    -3.64
     is
    -2.34
     no
    -2.23
     by
    -2.09
    up
    -1.95
     $
    -1.76
    You
    -1.75
    而又
    -1.73
     at
    -1.73
    by
    -1.72
    POSITIVE LOGITS
    ズニー
    2.52
     parfüm
    2.19
     sokak
    2.16
     diki
    2.05
     torba
    2.03
    錞
    2.02
     köp
    1.94
    蹓
    1.92
    ⽼
    1.91
     キーホルダー
    1.91
    Activations Density 0.003%

    No Known Activations