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. 173
    Prev
    Next
    INDEX
    Explanations

    introducing purpose or consequence

    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
     because
    -1.57
     and
    -1.55
     eftersom
    -1.43
     since
    -1.40
     that
    -1.38
     dlatego
    -1.27
     omdat
    -1.23
     потому
    -1.16
     ponieważ
    -1.15
     protože
    -1.13
    POSITIVE LOGITS
     they
    2.31
     we
    1.92
     cuando
    1.75
     ketika
    1.73
     можно
    1.69
     lorsque
    1.64
     can
    1.59
     nantinya
    1.59
     later
    1.57
     można
    1.53
    Activations Density 0.029%

    No Known Activations