© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    emojis introducing text elements

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     excision
    0.79
     conveyance
    0.75
     transactions
    0.71
    ۱
    0.71
     prowess
    0.69
     message
    0.68
     malicious
    0.67
     surveyor
    0.67
    ва
    0.66
     від
    0.66
    POSITIVE LOGITS
    ك
    1.16
    ف
    0.99
    شي
    0.90
    ের
    0.90
    s
    0.86
    <0x0D>
    0.86
    ters
    0.85
    \
    0.84
    :
    0.84
    كور
    0.84
    Activations Density 0.311%

    No Known Activations