© 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. 13233
    Prev
    Next
    INDEX
    Explanations

    numbers, versions, and abbreviations

    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
     เนื่องจาก
    0.54
     Jennifer
    0.46
     επίσης
    0.46
    ת
    0.45
     এমন
    0.45
    其他
    0.45
     Α
    0.45
    েন্দু
    0.44
     Alan
    0.44
     especializada
    0.44
    POSITIVE LOGITS
    2
    0.72
    :
    0.70
     for
    0.63
    _
    0.60
     are
    0.59
    ۲
    0.59
    1
    0.54
    for
    0.53
    ²
    0.53
     that
    0.52
    Activations Density 0.166%

    No Known Activations