© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169329
    Prev
    Next
    INDEX
    Explanations

    logical structure

    np_acts-logits-general · gemini-2.5-flash-lite

    American politics and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ச்சர்
    0.44
     rosy
    0.42
     takiego
    0.41
     nominations
    0.41
     nominated
    0.40
    <unused38>
    0.39
    THRESH
    0.39
     DISCLAIMED
    0.39
     pergunta
    0.39
    ވާ
    0.39
    POSITIVE LOGITS
                     
    0.51
    Vm
    0.50
     minuscule
    0.50
     攵
    0.50
     Logic
    0.49
    Windows
    0.48
          
    0.48
     logique
    0.47
    逻辑
    0.47
                   
    0.46
    Activations Density 0.001%

    No Known Activations