© 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. 138
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     остро
    -1.30
    踌
    -1.28
    委会
    -1.27
    姉妹
    -1.23
     دعم
    -1.23
     kılı
    -1.23
     進
    -1.23
    カオ
    -1.21
     년
    -1.20
    幼児
    -1.20
    POSITIVE LOGITS
    文化
    1.29
    世
    1.28
    ")
    1.28
     ως
    1.27
    ;”
    1.25
    これは
    1.25
    </h2>
    1.24
    ূ
    1.24
    ”:
    1.23
     Chá
    1.23
    Activations Density 0.015%

    No Known Activations