© 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. 226701
    Prev
    Next
    INDEX
    Explanations

    buy, sale, money, step

    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
     கவன
    0.51
     shrewd
    0.45
     hurriedly
    0.44
    =[]
    0.43
    ću
    0.43
     bombed
    0.43
    )\
    0.43
     spirited
    0.43
     hurried
    0.42
    )}>
    0.41
    POSITIVE LOGITS
     Subram
    0.48
    ینه
    0.45
     sehat
    0.45
     Az
    0.45
     Tä
    0.45
    rikes
    0.43
     sial
    0.43
    のは
    0.43
     by
    0.43
     अन्न
    0.42
    Activations Density 0.001%

    No Known Activations