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. 8251
    Prev
    Next
    INDEX
    Explanations

    Clu, Klu starters with subsequent endings

    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
     Porte
    -0.87
     Sumer
    -0.79
    umer
    -0.77
    building
    -0.74
    adores
    -0.73
     blown
    -0.71
     Hawks
    -0.71
     Numer
    -0.71
    Building
    -0.71
     Lightning
    -0.71
    POSITIVE LOGITS
    Clu
    0.98
     Clu
    0.92
     clu
    0.89
    fikasi
    0.80
     claves
    0.69
     BIBSYS
    0.69
    当初
    0.68
     gew
    0.68
    一般
    0.67
    enaar
    0.66
    Activations Density 0.016%

    No Known Activations