© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    also use or look

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

    alternative methods or actions

    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
    无疑
    0.48
    毕竟
    0.45
     மட்டுமே
    0.43
    ՛
    0.41
     afore
    0.41
    众人
    0.40
     ഒരാ
    0.40
    可谓
    0.40
     regering
    0.40
    偿
    0.39
    POSITIVE LOGITS
     describe
    0.45
     그래프
    0.43
     другую
    0.41
    describe
    0.41
    Describe
    0.40
     Describe
    0.40
     точку
    0.40
     poprzez
    0.39
     функцию
    0.39
     إنشاء
    0.39
    Activations Density 0.001%

    No Known Activations