© 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. 37023
    Prev
    Next
    INDEX
    Explanations

    final trick

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

    also, can, or, could

    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
     Zuge
    0.49
    igator
    0.48
     IoT
    0.43
    <0x0D>
    0.42
    igned
    0.42
     aged
    0.42
    cham
    0.42
     rebound
    0.41
     renter
    0.41
     Torres
    0.40
    POSITIVE LOGITS
     çalışmaları
    0.49
     हजारों
    0.46
    很多
    0.46
    秞
    0.44
     многих
    0.43
     কারণেই
    0.43
     vardır
    0.43
    فاوت
    0.43
     skoro
    0.43
    许
    0.43
    Activations Density 0.000%

    No Known Activations