© 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. 74881
    Prev
    Next
    INDEX
    Explanations

    command line 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
    
    -3.11
    鋮
    -3.00
    蟜
    -2.92
    
    -2.81
    晅
    -2.75
     \&
    -2.66
     всѣ
    -2.63
    鹋
    -2.52
    劻
    -2.52
    alties
    -2.52
    POSITIVE LOGITS
    >
    3.06
    t
    2.86
    ↵↵
    2.64
     
    2.59
    -
    2.59
     meek
    2.33
    self
    2.27
    If
    2.23
     resting
    2.22
    点了点头
    2.22
    Activations Density 0.004%

    No Known Activations