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. 7884
    Prev
    Next
    INDEX
    Explanations

    DOI suffixes

    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
     Plu
    -0.93
    Plu
    -0.84
    ativ
    -0.78
     Tail
    -0.77
     thrones
    -0.77
     Takeaways
    -0.77
    île
    -0.76
     Zivil
    -0.75
     Makeup
    -0.73
     جات
    -0.73
    POSITIVE LOGITS
    olto
    0.81
     rū
    0.77
    cljs
    0.74
     manifestaciones
    0.73
    量の
    0.72
    ึกษา
    0.72
     inútil
    0.72
    automation
    0.72
    enal
    0.71
     Wohl
    0.70
    Activations Density 0.008%

    No Known Activations