© 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. 3049
    Prev
    Next
    INDEX
    Explanations

    comparing, searching, news, data

    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
     přímo
    0.48
     pots
    0.44
    ä
    0.44
     nuestras
    0.43
     naše
    0.42
     niñas
    0.41
    する
    0.41
     nasze
    0.41
    َّا
    0.41
     देती
    0.41
    POSITIVE LOGITS
     StringVar
    0.51
     Touchable
    0.46
     Сак
    0.46
     Жи
    0.45
     ChIP
    0.45
     choker
    0.45
    ները
    0.44
     Э
    0.44
    最具
    0.44
    ขึ้น
    0.44
    Activations Density 0.001%

    No Known Activations