© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50837
    Prev
    Next
    INDEX
    Explanations

    shutil, save, stress, spices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x0D>
    0.49
     উপভোগ
    0.47
     illetve
    0.46
     notoriously
    0.45
     sustainably
    0.44
     conventionally
    0.44
     ashore
    0.42
     archae
    0.42
     transatlantic
    0.42
    IR
    0.41
    POSITIVE LOGITS
     ሂደ
    0.48
    侄
    0.43
     ಕೆಲಸ
    0.41
    新しい
    0.41
    िफिकेट
    0.39
     분석
    0.39
     少し
    0.39
     그래프
    0.38
    납
    0.38
     새로운
    0.38
    Activations Density 0.013%

    No Known Activations