Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8517
    Prev
    Next
    INDEX
    Explanations

    programming language versions and frameworks

    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_34/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
    manteau
    -0.87
    ふるさと
    -0.84
    ylvanian
    -0.79
     pierwszym
    -0.77
    bisch
    -0.76
    駅前
    -0.76
     Utama
    -0.76
     balne
    -0.75
    lllllll
    -0.74
    Informazioni
    -0.74
    POSITIVE LOGITS
     newer
    1.44
     JDK
    1.40
     >=
    1.35
    jdk
    1.34
     версии
    1.26
    JDK
    1.23
     older
    1.22
     Python
    1.18
     versions
    1.16
     newest
    1.12
    Activations Density 0.304%

    No Known Activations