© 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. 103470
    Prev
    Next
    INDEX
    Explanations

    Ownership and numbers

    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
     emphasize
    0.48
    講
    0.47
    🥲
    0.47
    I
    0.46
    aties
    0.46
    V
    0.46
    School
    0.46
     dataset
    0.45
    Seg
    0.45
    ట్‌
    0.45
    POSITIVE LOGITS
     بالټ
    0.53
    rabbit
    0.52
     Karo
    0.51
     বাজারের
    0.51
     விற்ப
    0.50
    rvGroup
    0.50
    ⦕
    0.50
    wallepics
    0.49
    říklad
    0.49
    tsprec
    0.49
    Activations Density 0.002%

    No Known Activations