© 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. 152783
    Prev
    Next
    INDEX
    Explanations

    fees, restaurants, record

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

    institution processing

    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
    piel
    0.46
    Bub
    0.45
    
    0.45
     כמו
    0.45
    (")
    0.44
    REFERENCE
    0.43
     Roswell
    0.43
     bevor
    0.43
    Woods
    0.43
    玥
    0.43
    POSITIVE LOGITS
    น
    0.48
    ส
    0.47
    サ
    0.47
    いろいろ
    0.45
     transporting
    0.44
     পরিবহন
    0.44
    집
    0.44
    стоит
    0.43
    があります
    0.43
    മ്
    0.42
    Activations Density 0.001%

    No Known Activations