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. 8223
    Prev
    Next
    INDEX
    Explanations

    decades

    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
     degli
    -0.87
     eighteenth
    -0.84
     nineteenth
    -0.79
     hochwertige
    -0.79
     barva
    -0.78
    팍
    -0.77
     đôi
    -0.76
     prostor
    -0.75
    きち
    -0.75
    这件事情
    -0.75
    POSITIVE LOGITS
     ’
    1.05
    IONA
    0.90
    ARP
    0.85
    gré
    0.83
    ceria
    0.82
    槿
    0.81
     dansk
    0.81
    bles
    0.79
    pear
    0.78
    力が
    0.77
    Activations Density 0.021%

    No Known Activations