© 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. 10318
    Prev
    Next
    INDEX
    Explanations

    publications in journals

    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
     himself
    -1.69
     about
    -1.56
    の部分
    -1.41
     sostu
    -1.31
     パッド
    -1.27
     cũng
    -1.27
     erforder
    -1.24
    尛
    -1.22
    ריות
    -1.22
    鐿
    -1.20
    POSITIVE LOGITS
     unsere
    1.37
    ADORES
    1.33
    </strong>
    1.26
     an
    1.24
    يا
    1.23
     concepts
    1.21
     findings
    1.19
     more
    1.16
    НИЯ
    1.16
     most
    1.15
    Activations Density 0.034%

    No Known Activations