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. 8237
    Prev
    Next
    INDEX
    Explanations

    mathematical annotations with variables

    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
     finally
    -0.98
     only
    -0.96
     also
    -0.96
     Darstellung
    -0.94
    も多く
    -0.91
     merely
    -0.90
     able
    -0.89
     what
    -0.89
     many
    -0.86
     who
    -0.84
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.96
     Anyways
    0.95
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.94
    Ecco
    0.94
     forza
    0.93
    售后
    0.91
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.91
     Gebruik
    0.91
    的实力
    0.90
     Nedir
    0.90
    Activations Density 0.038%

    No Known Activations