© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32049
    Prev
    Next
    INDEX
    Explanations

    rinsing and cleaning

    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
    _
    0.78
    é
    0.76
    ۰
    0.75
    ian
    0.74
    :
    0.72
    se
    0.71
     resistance
    0.67
    อย่าง
    0.67
    ;
    0.67
     =
    0.67
    POSITIVE LOGITS
    م
    0.87
    ться
    0.82
    ள்ளனர்
    0.82
    ומי
    0.79
    다면
    0.78
    ف
    0.77
    وم
    0.77
    imizde
    0.76
    ತೆಗೆ
    0.75
    imizi
    0.74
    Activations Density 0.002%

    No Known Activations