© 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-16K
    7. 11345
    Prev
    Next
    INDEX
    Explanations

    Boston Marathon bombing investigation

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

    complex physics and shapes

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ettes
    0.45
    з
    0.45
    зи
    0.43
    ety
    0.43
    ೂರ್
    0.43
    elling
    0.43
    ap
    0.42
    виа
    0.41
    clf
    0.41
    ста
    0.40
    POSITIVE LOGITS
     Перейти
    0.48
     Porsche
    0.48
     Մ
    0.47
     Leandro
    0.46
     लह
    0.45
     பல்வேறு
    0.44
    বিভিন্ন
    0.44
     વિવિધ
    0.43
    行动
    0.43
     የተለያዩ
    0.42
    Activations Density 0.007%

    No Known Activations