© 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. 171915
    Prev
    Next
    INDEX
    Explanations

    strategic predictions

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

    explaining what something means

    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
    澼
    0.50
     नं
    0.46
     сумка
    0.46
     بذ
    0.46
     stö
    0.45
     पिस्टल
    0.44
     ஆல்
    0.44
     ਹ
    0.44
     அனைத்து
    0.44
     часу
    0.44
    POSITIVE LOGITS
     strategic
    0.54
     derived
    0.48
     reinvent
    0.47
     restricted
    0.46
     দার
    0.46
    strategic
    0.45
     strategically
    0.45
     transformative
    0.44
     featuring
    0.44
     derive
    0.44
    Activations Density 0.001%

    No Known Activations