© 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. 99206
    Prev
    Next
    INDEX
    Explanations

    programmatic and introductory text

    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
    glied
    -1.67
    焢
    -1.57
    狲
    -1.56
    
    -1.55
     creat
    -1.52
     excès
    -1.51
    /
    -1.49
     dji
    -1.48
     réinitial
    -1.47
    瓛
    -1.46
    POSITIVE LOGITS
     There
    1.87
     However
    1.77
     Ironically
    1.70
     Thankfully
    1.61
     Basically
    1.59
     respective
    1.59
     Surprisingly
    1.56
     Fortunately
    1.55
     Roughly
    1.53
     Unfortunately
    1.49
    Activations Density 0.000%

    No Known Activations