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. 8119
    Prev
    Next
    INDEX
    Explanations

    court of appeals or proceedings

    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
     obvious
    -0.97
     grouped
    -0.95
     personnel
    -0.90
    ervant
    -0.87
    Bibliografie
    -0.85
    先の
    -0.84
     foolish
    -0.83
     conditions
    -0.83
     rápida
    -0.82
     進
    -0.82
    POSITIVE LOGITS
     of
    2.22
    OfThe
    1.03
     from
    1.02
    seventh
    0.97
    более
    0.94
     achten
    0.93
     Mexique
    0.92
     της
    0.90
     the
    0.90
    только
    0.90
    Activations Density 0.007%

    No Known Activations