© 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. 106381
    Prev
    Next
    INDEX
    Explanations

    provided information

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

    bought or sold, assessments

    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
     Бекер
    0.61
    梠
    0.55
    损伤
    0.52
    ！
    0.52
     Результа
    0.48
    벧
    0.47
    依旧
    0.47
    善
    0.47
    傈
    0.47
    尽可能
    0.46
    POSITIVE LOGITS
    čná
    0.49
    čný
    0.48
    ायचे
    0.47
     concentrated
    0.46
    wei
    0.45
     tepl
    0.45
     dingen
    0.45
     விட
    0.45
     administered
    0.44
     moderated
    0.44
    Activations Density 0.002%

    No Known Activations