© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116381
    Prev
    Next
    INDEX
    Explanations

    number and citation

    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
    per
    -0.75
     permit
    -0.74
    istar
    -0.68
     прове
    -0.68
    "](
    -0.67
    许可
    -0.67
    льше
    -0.66
    ське
    -0.66
     Condol
    -0.65
    isseau
    -0.64
    POSITIVE LOGITS
     bouquets
    0.79
     малю
    0.79
     logarithms
    0.78
    Obtener
    0.77
    tienen
    0.75
     Devlin
    0.74
    VEGF
    0.73
    enlace
    0.72
    函数
    0.72
     paranoia
    0.71
    Activations Density 0.280%

    No Known Activations