© 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. 22-GEMMASCOPE-RES-131K
    7. 54298
    Prev
    Next
    INDEX
    Explanations

    properly

    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_22/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
     just
    -1.89
     actionTypes
    -1.87
    そして
    -1.82
    ୈ
    -1.82
     two
    -1.81
     those
    -1.77
     three
    -1.75
     eight
    -1.74
    
    -1.72
     both
    -1.70
    POSITIVE LOGITS
    すっ
    2.42
    ところに
    2.17
    為に
    2.16
    マジで
    2.14
    ふと
    2.14
    感じで
    2.13
    凄く
    1.98
    きち
    1.96
    ほら
    1.94
    ビックリ
    1.91
    Activations Density 0.011%

    No Known Activations