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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 41973
    Prev
    Next
    INDEX
    Explanations

    Purdue OWL, ribosomes

    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
     程序
    0.67
     elég
    0.66
    囝
    0.66
     企业
    0.65
    Connector
    0.64
     verletzt
    0.63
     produse
    0.62
     Eink
    0.61
     eus
    0.61
     Dutton
    0.61
    POSITIVE LOGITS
    ล
    0.73
     ک
    0.64
    춧
    0.63
     वि
    0.62
    وی
    0.62
    τίας
    0.62
    a
    0.60
    ک
    0.59
    ز
    0.59
    <0x0D>
    0.59
    Activations Density 0.000%

    No Known Activations