© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24504
    Prev
    Next
    INDEX
    Explanations

    Or, Orb, Orisa, Orca

    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_40_width_262k_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
    diction
    0.39
     中的
    0.39
    零部件
    0.38
    有两种
    0.38
     liberd
    0.37
    跟
    0.37
    Ы
    0.36
    니까
    0.35
    
    0.35
    ىم
    0.35
    POSITIVE LOGITS
    Or
    0.42
     Or
    0.40
     punching
    0.39
     Orc
    0.37
     Ор
    0.37
     приветствую
    0.36
    オル
    0.35
    賊
    0.35
    質
    0.35
     ор
    0.34
    Activations Density 0.006%

    No Known Activations