© 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. 225100
    Prev
    Next
    INDEX
    Explanations

    concomitant atrial fibrillation

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

    robust safety or established standards

    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
    пла
    0.53
     автобу
    0.49
    па
    0.48
    мос
    0.47
     より
    0.47
     ОТ
    0.47
     か
    0.46
    되고
    0.46
     кирпи
    0.46
     составляют
    0.45
    POSITIVE LOGITS
     κοινων
    0.41
     Hollywood
    0.40
     intuition
    0.40
     Sig
    0.39
     henne
    0.39
     Diving
    0.39
     hollywood
    0.39
     Gigi
    0.38
     promote
    0.38
    匠
    0.38
    Activations Density 0.002%

    No Known Activations