© 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. 217949
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    numbers and basis

    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
    ons
    0.44
    idences
    0.44
    ères
    0.44
    AL
    0.42
    フード
    0.42
    唪
    0.42
    bons
    0.41
    փ
    0.41
    F
    0.40
     altres
    0.40
    POSITIVE LOGITS
     nonetheless
    0.48
     最後
    0.47
     تعريف
    0.47
     usually
    0.47
     نهاية
    0.46
     genealog
    0.45
     أثناء
    0.45
     constitution
    0.45
     require
    0.45
     живу
    0.44
    Activations Density 0.000%

    No Known Activations