© 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. 10-GEMMASCOPE-RES-131K
    7. 104918
    Prev
    Next
    INDEX
    Explanations

    examines or explores

    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_10/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
     such
    -1.89
     with
    -1.51
    ﻪ
    -1.43
    潾
    -1.43
     修理
    -1.43
    ваш
    -1.41
     用品
    -1.40
     by
    -1.39
     termurah
    -1.37
    What
    -1.35
    POSITIVE LOGITS
     “
    1.72
     veulent
    1.29
     how
    1.27
     बीच
    1.25
    .”
    1.24
     της
    1.24
    ЕТ
    1.20
     étendue
    1.16
    茈
    1.15
    бира
    1.14
    Activations Density 0.098%

    No Known Activations