© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116773
    Prev
    Next
    INDEX
    Explanations

    THIS WEEK

    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
     бетон
    -1.02
     خودش
    -1.02
     blusa
    -0.94
    ousand
    -0.93
     boundless
    -0.93
     fazendo
    -0.93
     THOSE
    -0.93
    ма
    -0.92
     aktuelle
    -0.90
    hander
    -0.90
    POSITIVE LOGITS
    Despite
    1.09
    地说
    1.04
     examined
    1.01
    進行
    1.00
     despite
    1.00
     potranno
    0.99
     خواهید
    0.97
     allows
    0.96
     strategies
    0.94
     彈
    0.94
    Activations Density 0.001%

    No Known Activations