© 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. 45016
    Prev
    Next
    INDEX
    Explanations

    order and event status

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

    instead, switching, escape

    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
    而且
    0.51
    và
    0.49
     очень
    0.48
     itd
    0.47
    有一个
    0.47
     而且
    0.46
     naprawdę
    0.45
    很
    0.45
    是怎么
    0.45
     và
    0.44
    POSITIVE LOGITS
    導致
    0.53
     frustrated
    0.50
     نئے
    0.49
     indignant
    0.47
     Instead
    0.46
     aggrieved
    0.46
     উপায়
    0.45
    代わりに
    0.45
     वापस
    0.44
     abandoning
    0.44
    Activations Density 0.000%

    No Known Activations