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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57477
    Prev
    Next
    INDEX
    Explanations

    configuration attributes

    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
     even
    -1.13
    izando
    -1.08
     also
    -1.00
    の基本
    -0.98
    也有
    -0.98
    wan
    -0.97
     danych
    -0.97
    -\\
    -0.96
    eren
    -0.96
    ="
    -0.95
    POSITIVE LOGITS
     tedy
    1.09
     худо
    1.04
     می‌کنند
    1.02
    льзя
    1.01
     cenas
    0.98
     damaligen
    0.97
     Therefore
    0.97
     gamla
    0.95
     इसलिए
    0.94
    光是
    0.94
    Activations Density 0.177%

    No Known Activations