© 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. 34-GEMMASCOPE-RES-131K
    7. 106833
    Prev
    Next
    INDEX
    Explanations

    programming problem solutions

    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_34/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
    靭
    -0.77
    靱
    -0.76
     lentil
    -0.76
    тельную
    -0.75
    開店
    -0.75
     změ
    -0.74
    ฌ
    -0.73
    Vé
    -0.73
     multipart
    -0.72
     RICO
    -0.71
    POSITIVE LOGITS
     challenge
    1.70
     problem
    1.61
     solution
    1.60
     solutions
    1.55
     challenges
    1.50
     leetcode
    1.42
    leetcode
    1.40
     solving
    1.37
     Solutions
    1.35
     Challenge
    1.34
    Activations Density 0.231%

    No Known Activations