© 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. 30163
    Prev
    Next
    INDEX
    Explanations

    multilingual or numeric lists

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

    subject vs object

    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
    왜
    0.43
     meest
    0.42
     coches
    0.42
     coars
    0.41
     veins
    0.41
     thema
    0.40
     Mbps
    0.39
    aksha
    0.39
     kracht
    0.39
    chter
    0.39
    POSITIVE LOGITS
    䐪
    0.49
     బ్యాంకు
    0.47
    lectual
    0.47
     πα
    0.46
    illaume
    0.45
     সদ্য
    0.45
    郋
    0.44
     Πα
    0.44
    েষ
    0.43
     নির্বাচনী
    0.43
    Activations Density 0.000%

    No Known Activations