© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54139
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
     večer
    -1.10
     creativo
    -1.05
     kalite
    -1.03
    ではなく
    -1.02
     baisse
    -1.01
     intermedio
    -1.01
     ofici
    -1.00
     relatório
    -1.00
     organizes
    -1.00
     copious
    -1.00
    POSITIVE LOGITS
    </strong>
    1.19
    </i>
    1.05
     “
    1.05
    Ò
    0.99
    ❉
    0.98
    </u>
    0.97
    ,.
    0.95
    ~
    0.94
    Õ
    0.94
    ray
    0.94
    Activations Density 0.005%

    No Known Activations