© 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. 130715
    Prev
    Next
    INDEX
    Explanations

    quantifiers and follow-ups

    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
    ↵↵
    -3.48
     
    -3.08
    R
    -2.67
      
    -2.61
    T
    -2.34
    -
    -2.34
    D
    -2.34
    S
    -2.33
     I
    -2.31
    B
    -2.27
    POSITIVE LOGITS
    vantaged
    2.91
    While
    2.88
    When
    2.86
     și
    2.72
     粉色
    2.63
     및
    2.61
    It
    2.59
    </h3>
    2.56
    媜
    2.53
    jewództ
    2.44
    Activations Density 0.000%

    No Known Activations