© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings and numbers

    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
    acja
    -0.85
     дверь
    -0.79
     fatica
    -0.78
    彰化
    -0.77
     always
    -0.76
     actually
    -0.76
     Actually
    -0.75
     different
    -0.74
     pasaba
    -0.73
    ﻝ
    -0.73
    POSITIVE LOGITS
     Fren
    0.95
     Fridays
    0.80
     Akade
    0.79
     الموا
    0.78
     タンク
    0.75
    烟
    0.75
     deposed
    0.74
    Friday
    0.74
     choo
    0.71
    廣
    0.71
    Activations Density 0.336%

    No Known Activations