© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70642
    Prev
    Next
    INDEX
    Explanations

    teachers and professors

    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
    他們的
    -1.67
     élégante
    -1.63
     homepage
    -1.49
    三個
    -1.48
    jetas
    -1.48
     любого
    -1.43
    Exeunt
    -1.42
     زیبا
    -1.39
    ihnach
    -1.39
     Eigentü
    -1.38
    POSITIVE LOGITS
     and
    2.22
     this
    1.46
     also
    1.42
     such
    1.41
    ner
    1.36
    <i>
    1.30
    也
    1.28
    🙌
    1.26
    也是
    1.26
    🤣🤣
    1.24
    Activations Density 0.027%

    No Known Activations