© 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. 7117
    Prev
    Next
    INDEX
    Explanations

    numbers and specific sequences

    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
     瑞
    -0.77
     genitori
    -0.77
     ошибки
    -0.75
    🥩
    -0.73
    كما
    -0.73
    Obsah
    -0.73
    🔫
    -0.72
    現在の
    -0.72
    Personality
    -0.71
    높
    -0.71
    POSITIVE LOGITS
    recovery
    0.87
     recovery
    0.77
     snar
    0.77
     slower
    0.75
    拖
    0.75
     nạn
    0.74
     levou
    0.74
    ReadByte
    0.73
     durchschnitt
    0.73
     shorten
    0.73
    Activations Density 0.006%

    No Known Activations