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. 85
    Prev
    Next
    INDEX
    Explanations

    citations and dates

    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
     eight
    -1.31
     nine
    -1.28
    With
    -1.27
     five
    -1.27
    Those
    -1.24
     four
    -1.21
     six
    -1.20
     seven
    -1.17
    Despite
    -1.13
     undeniably
    -1.10
    POSITIVE LOGITS
    があり
    1.28
     opulent
    1.27
     extremely
    1.27
     molte
    1.27
     whimsical
    1.26
     famed
    1.23
     trám
    1.20
     postulated
    1.18
     crappy
    1.16
    owane
    1.15
    Activations Density 0.020%

    No Known Activations