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. 8453
    Prev
    Next
    INDEX
    Explanations

    title, post, links, season, Attorney, edit

    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
    adlo
    -0.77
    deelte
    -0.73
    joit
    -0.73
     Olympedia
    -0.72
    である
    -0.70
     Worm
    -0.69
    IAS
    -0.68
    ्स
    -0.66
    Managing
    -0.65
    æng
    -0.65
    POSITIVE LOGITS
     mø
    0.76
    rů
    0.75
     wyn
    0.74
     друзьями
    0.74
    yed
    0.73
     STEIN
    0.73
     desain
    0.73
     doppio
    0.72
     kaya
    0.72
    jana
    0.71
    Activations Density 0.024%

    No Known Activations