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. 219
    Prev
    Next
    INDEX
    Explanations

    court orders

    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
     our
    -1.07
     we
    -0.87
    我们可以
    -0.83
    GARY
    -0.81
    b
    -0.79
    普及
    -0.77
     TCG
    -0.77
     nuestro
    -0.76
     μας
    -0.76
    ׇ
    -0.76
    POSITIVE LOGITS
     federal
    0.98
    ORDER
    0.95
    &(
    0.91
    üman
    0.90
     Adventure
    0.88
    currently
    0.88
     ファミ
    0.87
    phonic
    0.83
    zsef
    0.83
     gebre
    0.82
    Activations Density 0.120%

    No Known Activations