© 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. 249945
    Prev
    Next
    INDEX
    Explanations

    product line

    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
    でしたが
    0.45
    겠지만
    0.45
    다
    0.45
    했지만
    0.44
    았습니다
    0.44
    ா
    0.43
     kalem
    0.41
     छोटी
    0.40
     small
    0.40
    ാ
    0.39
    POSITIVE LOGITS
     Schauspiel
    0.50
     Jego
    0.48
     উত্তেজ
    0.47
    にて
    0.47
     umożliw
    0.46
     utilisent
    0.46
     revêtu
    0.45
    roben
    0.45
    tcpHeader
    0.45
     Nutr
    0.44
    Activations Density 0.000%

    No Known Activations