© 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-262K
    7. 43988
    Prev
    Next
    INDEX
    Explanations

    German, Belgian, and Kafkaesque terms

    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_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
     saddhim
    0.48
     நிற்க
    0.47
     تقسيم
    0.47
    ählten
    0.44
    }$;
    0.43
    цька
    0.42
     няколко
    0.42
    กล
    0.42
     संकेत
    0.41
    MyToolkit
    0.41
    POSITIVE LOGITS
     BLUE
    0.49
    Μ
    0.46
     menu
    0.45
     Blue
    0.45
     Programm
    0.42
    の世界
    0.42
     Menu
    0.42
     Casino
    0.42
    RGB
    0.42
    Ν
    0.42
    Activations Density 0.001%

    No Known Activations