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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8203
    Prev
    Next
    INDEX
    Explanations

    inspired by classic or past styles

    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
     này
    -1.09
    了一会儿
    -1.05
    接種
    -1.04
    هذه
    -1.04
    satunya
    -1.02
    窺
    -0.98
    翌日
    -0.94
     or
    -0.93
    ?(
    -0.93
     pursuant
    -0.91
    POSITIVE LOGITS
     célèbre
    1.47
     traditions
    1.39
     the
    1.38
     classic
    1.34
     classical
    1.34
     klas
    1.30
     past
    1.28
     cultures
    1.27
     renowned
    1.25
     cláss
    1.24
    Activations Density 0.057%

    No Known Activations