© 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. 103678
    Prev
    Next
    INDEX
    Explanations

    election dates and privileged sites

    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
    磡
    -0.70
    marginTop
    -0.68
    igan
    -0.68
    mox
    -0.66
     आवश्यक
    -0.66
     transfusion
    -0.66
    restrictions
    -0.66
    یمت
    -0.65
    ͆
    -0.65
    marine
    -0.64
    POSITIVE LOGITS
    factorial
    0.71
     smokes
    0.70
    뜻
    0.69
     build
    0.67
     Schmel
    0.66
     script
    0.66
     naturale
    0.66
    ffl
    0.66
     Supplies
    0.65
    PDM
    0.65
    Activations Density 0.061%

    No Known Activations