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. 8433
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    calips
    -1.00
     should
    -0.95
     syk
    -0.94
     has
    -0.92
     all
    -0.91
     those
    -0.91
     Desember
    -0.90
     some
    -0.90
     both
    -0.88
     their
    -0.88
    POSITIVE LOGITS
    ";
    1.06
    >";
    
    0.98
    うわ
    0.97
     zugel
    0.96
     verwendeten
    0.96
     vorhandenen
    0.95
     carcasa
    0.93
     wię
    0.93
    Lire
    0.89
    서울
    0.89
    Activations Density 0.000%

    No Known Activations