© 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. 83101
    Prev
    Next
    INDEX
    Explanations

    headings and code includes

    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
     persoons
    -0.86
     pseudos
    -0.81
    Ｈ
    -0.81
     turtleneck
    -0.79
     persönlichen
    -0.78
    呛
    -0.75
     numOf
    -0.75
     insensitive
    -0.75
    Erin
    -0.75
    宜蘭
    -0.75
    POSITIVE LOGITS
    加速
    0.85
    zels
    0.83
     istitu
    0.82
     moeda
    0.82
    azah
    0.81
    perrt
    0.81
    hti
    0.81
    surgery
    0.80
    pto
    0.79
    Será
    0.79
    Activations Density 0.008%

    No Known Activations