© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129295
    Prev
    Next
    INDEX
    Explanations

    finding the next word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    션을
    0.54
    ਟ
    0.45
    ताना
    0.43
    りを
    0.43
    Expiry
    0.43
    श
    0.43
    casual
    0.42
    clang
    0.41
    EM
    0.41
    우
    0.41
    POSITIVE LOGITS
    稆
    0.54
     fundraising
    0.48
     Electronic
    0.48
     British
    0.47
     Ně
    0.46
     Publishers
    0.45
     Historical
    0.45
     Research
    0.44
     Cal
    0.44
     Deportivo
    0.44
    Activations Density 0.012%

    No Known Activations