© 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. 334
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     несколь
    -0.91
     lagu
    -0.90
    urgeon
    -0.88
    angebote
    -0.80
     goc
    -0.80
    Модель
    -0.80
    🍤
    -0.79
    ícias
    -0.78
    //*
    -0.78
    ACEAE
    -0.77
    POSITIVE LOGITS
     $\
    0.96
    ,\\
    0.91
    \\
    0.91
    請繼續往下閱讀
    0.85
     \\
    0.84
    .\\
    0.81
     $\$
    0.81
     ${
    0.81
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.79
     $(\
    0.79
    Activations Density 0.075%

    No Known Activations