© 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. 32519
    Prev
    Next
    INDEX
    Explanations

    language or specific terms

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

    LED, income, RSVP contexts

    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
     Electricity
    0.51
     东
    0.49
    electricity
    0.48
     consignment
    0.46
     电
    0.45
    enaire
    0.44
     Duss
    0.44
    apos
    0.44
     Nuts
    0.44
     Nauk
    0.44
    POSITIVE LOGITS
     lồ
    0.53
    м
    0.52
     senhor
    0.45
     sàng
    0.45
     народов
    0.44
    讃
    0.44
     lỗ
    0.44
    ຕາມ
    0.44
    пло
    0.43
     conosce
    0.43
    Activations Density 0.000%

    No Known Activations