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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8516
    Prev
    Next
    INDEX
    Explanations

    specific language

    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
     to
    -1.26
     their
    -0.99
     exercí
    -0.98
     true
    -0.96
    tml
    -0.95
    erweise
    -0.94
     such
    -0.92
     have
    -0.91
    自作
    -0.90
     other
    -0.90
    POSITIVE LOGITS
    vocations
    1.16
     familières
    1.11
    zwischen
    1.07
     gånger
    1.05
    ÁN
    1.05
    orrho
    1.04
    mtable
    1.01
    Кто
    1.00
    ……”
    1.00
     котором
    1.00
    Activations Density 0.124%

    No Known Activations