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. 8416
    Prev
    Next
    INDEX
    Explanations

    founding of organizations and businesses

    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
     felpa
    -1.19
     wykonane
    -1.02
     again
    -1.02
     nuevamente
    -1.01
     députés
    -1.00
     nonostante
    -0.99
    Prepared
    -0.96
     sudadera
    -0.95
     zostanie
    -0.95
     Verhältnis
    -0.94
    POSITIVE LOGITS
     to
    2.42
     with
    1.61
     by
    1.57
     as
    1.46
     in
    1.41
     чтобы
    1.34
     out
    1.27
     מתוך
    1.25
     بهد
    1.17
    เพื่อ
    1.16
    Activations Density 0.109%

    No Known Activations