© 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. 205330
    Prev
    Next
    INDEX
    Explanations

    rose to, enables him to, for plastic, Friday prayers, sled during, restored him

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

    Nagasaki, needed, slopes, evaluate, constructed

    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
     Cite
    0.48
     優
    0.47
     衣
    0.47
     CaCl
    0.46
     δ
    0.46
    Poppins
    0.46
     Farr
    0.45
     Apply
    0.45
     Mag
    0.45
     抗
    0.45
    POSITIVE LOGITS
     financing
    0.57
    дування
    0.50
    та
    0.47
     terrace
    0.47
     retelling
    0.47
     tee
    0.47
     furthering
    0.45
     helicopter
    0.45
     sufficiency
    0.45
     fastening
    0.45
    Activations Density 0.001%

    No Known Activations