© 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. 146523
    Prev
    Next
    INDEX
    Explanations

    stories like yours

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

    troubleshooting instructions or problems

    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
    Not in Any Lists

    No Comments

    Negative Logits
    adeva
    0.54
    élim
    0.52
    elim
    0.48
    carbam
    0.47
     उबाल
    0.44
    kmeans
    0.43
     كتب
    0.42
     Д
    0.41
    basis
    0.41
    లేదు
    0.41
    POSITIVE LOGITS
    しております
    0.51
    年度
    0.46
    もら
    0.45
     Groom
    0.45
    𝓗
    0.45
     рік
    0.44
     goof
    0.44
    びに
    0.43
     overridden
    0.43
     paddingTop
    0.43
    Activations Density 0.000%

    No Known Activations