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. 129
    Prev
    Next
    INDEX
    Explanations

    like this

    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
     of
    -1.98
     to
    -1.36
     The
    -1.30
     Our
    -1.25
     I
    -1.21
    出了一
    -1.18
    ercizi
    -1.16
    T
    -1.16
     M
    -1.16
     is
    -1.15
    POSITIVE LOGITS
    :
    1.74
     légumes
    1.44
     jät
    1.41
     lää
    1.35
     作り方
    1.34
    ↑↑↑
    1.30
     rosado
    1.30
    Makanan
    1.29
    ※※
    1.28
    itado
    1.27
    Activations Density 0.120%

    No Known Activations