© 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. 77953
    Prev
    Next
    INDEX
    Explanations

    industry, available, government players

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

    requirements, carrier, relief, changing, spent

    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
    简介
    0.55
    味
    0.55
     όχι
    0.51
    传入
    0.50
    俩
    0.50
    介绍
    0.48
    进而
    0.48
     núcle
    0.47
     "<
    0.46
    明确
    0.46
    POSITIVE LOGITS
     chariot
    0.51
     decryption
    0.51
     PCD
    0.48
     valida
    0.47
    tariff
    0.45
    hone
    0.44
    OHN
    0.44
    sce
    0.43
    government
    0.43
    IsPass
    0.43
    Activations Density 0.000%

    No Known Activations