© 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. 85338
    Prev
    Next
    INDEX
    Explanations

    belt as accessory or singing loudly

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

    belt

    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
    Negative Logits
    温度
    0.52
     Temperatura
    0.50
     العلوم
    0.48
     TEMPERATURE
    0.48
     온도
    0.47
     Ammonium
    0.47
     температура
    0.47
    溫度
    0.47
    舜
    0.46
     SCHEDULE
    0.46
    POSITIVE LOGITS
     belt
    0.63
     belts
    0.59
    belt
    0.59
    Belt
    0.55
     Belt
    0.50
     waist
    0.47
    rell
    0.47
     gird
    0.47
     cint
    0.44
    irl
    0.43
    Activations Density 0.045%

    No Known Activations