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. 8268
    Prev
    Next
    INDEX
    Explanations

    the + noun

    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
    ܜ
    -1.33
     sogen
    -1.33
    鋮
    -1.22
    Those
    -1.19
     another
    -1.16
    Another
    -1.16
     aqueles
    -1.16
     those
    -1.15
    uario
    -1.13
     Jugendlichen
    -1.13
    POSITIVE LOGITS
     ambassade
    1.23
     robuste
    1.14
     rigide
    1.02
     ͡
    1.01
    mmmmmm
    0.99
     pantalon
    0.99
    🧍
    0.98
     votre
    0.97
    花の
    0.96
    髑
    0.96
    Activations Density 0.267%

    No Known Activations