© 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. 24246
    Prev
    Next
    INDEX
    Explanations

    ; banish, , to

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

    do not, will not

    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
    //
    0.43
     anders
    0.42
    践
    0.41
    Kaw
    0.40
    etzen
    0.40
     Gazetteer
    0.40
     Kaw
    0.39
    锄
    0.39
    Ec
    0.38
    Neighborhood
    0.38
    POSITIVE LOGITS
    ீ
    0.49
    
    0.48
    慜
    0.47
     व्यक्ती
    0.45
     মানুষকে
    0.44
     পদ্ধতিতে
    0.44
     केमिक
    0.44
    ೆಯೇ
    0.43
    ドラマ
    0.43
    សម្រាប់
    0.42
    Activations Density 0.000%

    No Known Activations