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. 8197
    Prev
    Next
    INDEX
    Explanations

    oil painting details

    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
     yakni
    -0.92
    随着
    -0.87
    
    -0.84
    ]){
    
    -0.82
     ـ
    -0.82
    ⍺
    -0.81
    жы
    -0.80
    DECLARE
    -0.79
    popd
    -0.79
     yaitu
    -0.79
    POSITIVE LOGITS
     Courtesy
    1.12
     detalle
    1.07
     courtesy
    1.07
     détail
    1.00
     oil
    0.98
    嬉しいです
    0.98
     museos
    0.97
     huile
    0.96
     NFS
    0.95
    怅
    0.94
    Activations Density 0.025%

    No Known Activations