© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217784
    Prev
    Next
    INDEX
    Explanations

    Mao Nixon Forbidden City

    np_acts-logits-general · gemini-2.5-flash-lite

    Great Wall, China, squares

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ध्व
    0.43
    払
    0.39
    명
    0.39
     koń
    0.37
    र्मु
    0.37
     결방
    0.35
    ಗೊಳ
    0.35
    ="\
    0.35
     हाइड्रो
    0.35
     Fest
    0.34
    POSITIVE LOGITS
     Reprinted
    0.43
     pouches
    0.42
     покра
    0.42
     CASA
    0.41
     speedometer
    0.41
     handbag
    0.40
     ketones
    0.39
     turismo
    0.39
     রাজপ
    0.39
     CLOS
    0.39
    Activations Density 0.009%

    No Known Activations