© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3516
    Prev
    Next
    INDEX
    Explanations

    HTTP web requests

    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_16_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
    uje
    0.96
    อย่าง
    0.89
    一
    0.89
    ра
    0.79
    ेटर
    0.79
    できる
    0.76
    変わ
    0.76
    รับ
    0.76
     अच्छा
    0.76
    تان
    0.76
    POSITIVE LOGITS
     on
    1.21
     propiedades
    0.87
    ↵
    0.87
     verr
    0.87
     y
    0.86
    ル
    0.84
     aulas
    0.79
     il
    0.78
     e
    0.78
     regalo
    0.77
    Activations Density 0.000%

    No Known Activations