© 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. 103300
    Prev
    Next
    INDEX
    Explanations

    section or content introduction

    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
     península
    -1.04
     maintenant
    -1.01
    æld
    -1.00
    Ռ
    -0.99
     armar
    -0.98
     või
    -0.96
    resti
    -0.96
    documentclass
    -0.95
     lourd
    -0.95
     guerr
    -0.94
    POSITIVE LOGITS
     type
    1.63
    type
    1.10
    >
    1.05
     प्रकार
    0.98
     inadequate
    0.98
    などは
    0.97
    タイプの
    0.96
    なども
    0.96
     types
    0.95
     and
    0.94
    Activations Density 0.000%

    No Known Activations