© 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. 34-GEMMASCOPE-RES-131K
    7. 38620
    Prev
    Next
    INDEX
    Explanations

    git commit -m

    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
     त
    -0.75
    답
    -0.74
    مارات
    -0.71
    klara
    -0.70
     akce
    -0.70
     knights
    -0.69
    mari
    -0.69
    Caches
    -0.69
     Knight
    -0.68
    椀
    -0.68
    POSITIVE LOGITS
     commit
    3.72
    commit
    3.31
     commits
    3.08
     committed
    3.02
    Commit
    2.98
     Commit
    2.91
    COMMIT
    2.78
     COMMIT
    2.77
     committing
    2.73
    committed
    2.41
    Activations Density 0.091%

    No Known Activations