© 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-262K
    7. 90681
    Prev
    Next
    INDEX
    Explanations

    recite poetry

    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
    Negative Logits
    ल
    1.02
    ;
    0.91
    ing
    0.89
     degrees
    0.87
    (
    0.84
     générales
    0.84
    ai
    0.79
    ק
    0.78
    م
    0.76
    elly
    0.76
    POSITIVE LOGITS
     recite
    0.91
    ،
    0.87
     It
    0.86
    what
    0.84
    зываем
    0.82
    tamil
    0.81
    шения
    0.80
     reciting
    0.80
    </h4>
    0.79
     recited
    0.79
    Activations Density 0.003%

    No Known Activations