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. 8334
    Prev
    Next
    INDEX
    Explanations

    http or https

    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
     out
    -1.10
     one
    -1.09
     because
    -1.08
    álbum
    -1.06
     inoxid
    -0.99
    بيل
    -0.96
     userManager
    -0.95
     evidently
    -0.94
     anivers
    -0.94
     ristoranti
    -0.94
    POSITIVE LOGITS
     három
    1.37
     begrenzt
    1.30
     thre
    1.28
     két
    1.27
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.24
     nieuwe
    1.23
     ,"
    1.22
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.21
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.21
     ___________
    1.20
    Activations Density 0.010%

    No Known Activations