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. 8169
    Prev
    Next
    INDEX
    Explanations

    explaining how something works or is used

    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
     or
    -1.54
     this
    -1.52
     because
    -1.44
     that
    -1.43
     such
    -1.36
     This
    -1.32
     which
    -1.26
     your
    -1.20
    ,
    -1.20
     omdat
    -1.17
    POSITIVE LOGITS
    /
    
    1.48
    .
    
    1.36
    .';
    1.29
    .'</
    1.29
    ۔
    1.24
     pomá
    1.16
    .'/
    1.15
    🧆
    1.12
    ;</
    1.09
    Alamat
    1.09
    Activations Density 0.073%

    No Known Activations