© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74780
    Prev
    Next
    INDEX
    Explanations

    gift card or certificate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     arriv
    0.52
     jok
    0.52
    3
    0.49
     يرد
    0.48
     gradu
    0.47
     fet
    0.47
     coment
    0.47
     fries
    0.46
     faute
    0.46
     dimens
    0.46
    POSITIVE LOGITS
    \}$,
    0.47
     ਜਾਂ
    0.47
    вшихся
    0.47
    ".*:
    0.46
     (^{
    0.46
    aratus
    0.46
    🛤
    0.46
     Ztg
    0.45
     Arzneim
    0.45
     лікар
    0.43
    Activations Density 0.001%

    No Known Activations