© 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. 128186
    Prev
    Next
    INDEX
    Explanations

    among other

    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
     
    -2.36
    {
    -2.14
    .
    -1.99
    ;
    -1.84
    </h1>
    -1.81
    A
    -1.78
     is
    -1.70
    +
    -1.55
    ↵↵↵
    -1.47
      
    -1.46
    POSITIVE LOGITS
    焢
    2.23
    卨
    2.05
    　　*
    1.98
     vilja
    1.91
    泺
    1.86
     べ
    1.86
     mentiras
    1.85
    曏
    1.84
    луйста
    1.82
     休閒
    1.82
    Activations Density 0.004%

    No Known Activations