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. 171
    Prev
    Next
    INDEX
    Explanations

    `word::token` or `word@token`

    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
    atech
    -0.82
    Iné
    -0.81
     Forder
    -0.74
     пад
    -0.73
     LOADING
    -0.71
     ESQ
    -0.71
     SKS
    -0.71
    edema
    -0.71
    Notif
    -0.71
     库
    -0.70
    POSITIVE LOGITS
     class
    1.08
    class
    1.03
     className
    0.97
    className
    0.93
    ND
    0.86
     InputDecoration
    0.85
    RELL
    0.81
    NG
    0.79
     const
    0.78
     Chees
    0.78
    Activations Density 0.005%

    No Known Activations