© 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. 109559
    Prev
    Next
    INDEX
    Explanations

    Copyright notices, permissions

    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
    érfi
    -0.71
     WELFARE
    -0.70
    opencv
    -0.69
     enough
    -0.69
     Mahan
    -0.67
    赶
    -0.66
     rumahnya
    -0.66
     Foundations
    -0.65
     erreichen
    -0.65
     happen
    -0.65
    POSITIVE LOGITS
    径
    0.78
    ätze
    0.74
    arter
    0.70
    hept
    0.70
     województ
    0.70
    SECON
    0.69
    segment
    0.67
     quar
    0.66
     Maka
    0.65
    зм
    0.65
    Activations Density 0.058%

    No Known Activations