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. 8123
    Prev
    Next
    INDEX
    Explanations

    licence

    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
     ellips
    -0.77
     Handle
    -0.74
     Logic
    -0.73
     문
    -0.70
    ellipse
    -0.69
    IERS
    -0.68
    lium
    -0.67
     read
    -0.67
    
    -0.66
     Про
    -0.66
    POSITIVE LOGITS
     Amo
    0.69
    änien
    0.67
     Bonne
    0.66
    ニーカー
    0.64
    Pwd
    0.63
     Marche
    0.62
    դ
    0.61
    ittens
    0.61
     schre
    0.61
    cognito
    0.60
    Activations Density 0.065%

    No Known Activations