© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 141715
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving numbers and operators

    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
     poderá
    0.62
    وغ
    0.60
    u
    0.52
     podrá
    0.52
    测试
    0.52
    if
    0.50
    o
    0.50
     algumas
    0.50
    ver
    0.50
    స్తు
    0.49
    POSITIVE LOGITS
     chipping
    0.51
    ਡੀ
    0.51
    謗
    0.51
     vestiges
    0.49
    কে
    0.49
     मुझे
    0.48
    かけ
    0.48
     sniping
    0.48
    を
    0.47
    ਜੀ
    0.47
    Activations Density 0.074%

    No Known Activations