© 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. 101601
    Prev
    Next
    INDEX
    Explanations

    quiz questions

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

    international and specific terms

    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
    Melitaea
    0.43
    шат
    0.42
    -;
    0.40
    ("_
    0.40
    сси
    0.39
     пари
    0.39
    мага
    0.39
    час
    0.39
    最高の
    0.39
     የ
    0.39
    POSITIVE LOGITS
     appunto
    0.55
     Inggris
    0.48
     UK
    0.47
     দিয়
    0.46
     konkrét
    0.46
     imz
    0.45
     mainland
    0.44
     perchè
    0.44
     sovereign
    0.42
     inglesa
    0.42
    Activations Density 0.001%

    No Known Activations