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. 8481
    Prev
    Next
    INDEX
    Explanations

    XML project configurations

    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
    uncia
    -0.89
     インスタ
    -0.85
     inalámbrico
    -0.84
     inalámb
    -0.84
    FOC
    -0.83
    풍
    -0.81
    artifactId
    -0.79
    BORDER
    -0.77
     Summar
    -0.76
     横浜
    -0.75
    POSITIVE LOGITS
     interesante
    0.81
     pretože
    0.80
    ":
    0.77
     LI
    0.75
     grew
    0.75
     Bag
    0.74
     тща
    0.73
    関連リンク
    0.73
    sprozess
    0.72
    eradish
    0.72
    Activations Density 0.002%

    No Known Activations