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. 8284
    Prev
    Next
    INDEX
    Explanations

    best/better part

    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
    between
    -0.90
    Else
    -0.87
     ngữ
    -0.82
     Things
    -0.81
     Sections
    -0.79
    Sections
    -0.79
    Compte
    -0.78
    cx
    -0.78
    things
    -0.78
    所
    -0.77
    POSITIVE LOGITS
     part
    2.27
     часть
    1.37
     część
    1.05
     части
    1.02
     części
    0.89
     parte
    0.85
     portion
    0.84
    部分は
    0.84
    chloride
    0.78
    enfone
    0.77
    Activations Density 0.103%

    No Known Activations