Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8668
    Prev
    Next
    INDEX
    Explanations

    purpose and significance

    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
     teñ
    -1.13
    Apre
    -1.05
     echar
    -1.02
     desenli
    -1.01
    Ingredi
    -0.99
    Недоліки
    -0.98
    Karakter
    -0.98
     соответству
    -0.97
     disfrutar
    -0.96
     cotidiana
    -0.96
    POSITIVE LOGITS
     of
    3.55
     towards
    1.94
    ของ
    1.51
     toward
    1.47
     between
    1.30
     to
    1.29
     của
    1.27
     for
    1.27
     from
    1.22
     that
    1.21
    Activations Density 0.131%

    No Known Activations