© 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. 69359
    Prev
    Next
    INDEX
    Explanations

    sequence after verb

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

    connecting words and phrases

    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
    正在
    0.48
    上演
    0.48
    趣
    0.48
    部屋
    0.47
    ﮔ
    0.47
     пространства
    0.46
     funer
    0.46
     ხელისუფ
    0.46
    空間
    0.45
    葬
    0.45
    POSITIVE LOGITS
     abbreviated
    0.54
     predetermined
    0.45
     Inventor
    0.45
     calomel
    0.44
     Clock
    0.44
     Examiner
    0.43
     egyszer
    0.43
     Tallahassee
    0.43
     reset
    0.42
     Zeiss
    0.42
    Activations Density 0.002%

    No Known Activations