© 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. 41-GEMMASCOPE-2-RES-262K
    7. 56691
    Prev
    Next
    INDEX
    Explanations

    unlikely phrases

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    等等
    0.46
     якобы
    0.46
    明显
    0.40
    ر
    0.40
    .),
    0.39
    .'),
    0.39
     hvis
    0.38
    .",[
    0.38
    رق
    0.37
    ূনতম
    0.37
    POSITIVE LOGITS
     surprising
    0.50
     nah
    0.50
     surprisingly
    0.47
     hardly
    0.47
     eher
    0.46
     Nah
    0.44
     in
    0.43
     rather
    0.42
     during
    0.41
     скорее
    0.41
    Activations Density 0.000%

    No Known Activations