© 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. 72953
    Prev
    Next
    INDEX
    Explanations

    keywords

    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
    फ़
    -1.56
    %\\
    -1.51
     soñ
    -1.48
    ším
    -1.48
     catalán
    -1.47
    。
    -1.46
    rasında
    -1.45
    （
    -1.45
     zwi
    -1.41
    :[{
    -1.41
    POSITIVE LOGITS
    imanapun
    1.43
     parlano
    1.41
    它的
    1.40
     it
    1.38
    もありますが
    1.37
     mengumumkan
    1.34
    Haber
    1.34
     abbiano
    1.31
    </h2>
    1.29
    Neder
    1.29
    Activations Density 0.158%

    No Known Activations