© 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. 250423
    Prev
    Next
    INDEX
    Explanations

    specific standalone words

    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
     Ο
    0.51
     უკ
    0.49
    ijuana
    0.49
     რუს
    0.48
     Sans
    0.48
    nce
    0.47
     Jun
    0.47
     बॉय
    0.47
    κια
    0.47
     フランス
    0.46
    POSITIVE LOGITS
    ))
    0.49
    ”
    0.49
     resorption
    0.47
     ricordo
    0.46
    iselle
    0.45
    身影
    0.44
    PE
    0.44
    跑到
    0.44
     pendientes
    0.44
     histology
    0.43
    Activations Density 0.000%

    No Known Activations