© 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. 118077
    Prev
    Next
    INDEX
    Explanations

    data provided

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

    confirming understanding

    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
     ଆ
    0.53
    ，《
    0.50
    áz
    0.47
     ಅವನು
    0.45
     電動
    0.43
    ="$
    0.43
     添加
    0.43
     $'
    0.43
    zij
    0.42
    enzo
    0.42
    POSITIVE LOGITS
     appearance
    0.47
    萸
    0.45
     terminé
    0.43
     comporte
    0.42
     soreness
    0.41
     ocasi
    0.41
     painful
    0.40
     Talking
    0.39
     haemorrh
    0.39
     किनार
    0.39
    Activations Density 0.002%

    No Known Activations