© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128539
    Prev
    Next
    INDEX
    Explanations

    names and "negligible"

    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
    ↵
    -3.98
    ↵↵
    -3.25
    -3.16
    0
    -2.89
    ide
    -2.66
     komplette
    -2.63
    i
    -2.45
      
    -2.45
     dritte
    -2.44
     $\
    -2.36
    POSITIVE LOGITS
     taky
    2.72
    饪
    2.70
    冏
    2.69
    偌
    2.53
     bojo
    2.47
    轵
    2.47
    埸
    2.44
    蹰
    2.44
    🪬
    2.44
    
    2.42
    Activations Density 0.007%

    No Known Activations