© 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-16K
    7. 6428
    Prev
    Next
    INDEX
    Explanations

    then your

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     сопро
    0.49
    -
    0.49
    िंग
    0.42
    ów
    0.42
    ier
    0.41
     मुकदमा
    0.41
    ēng
    0.41
     क्यू
    0.41
     bởi
    0.41
     samochod
    0.41
    POSITIVE LOGITS
     ඉතා
    0.52
     وكذلك
    0.49
     Polarization
    0.48
    驄
    0.48
     ძალიან
    0.46
    無論
    0.46
    ATING
    0.46
     very
    0.44
    আমাদের
    0.44
     THE
    0.44
    Activations Density 0.066%

    No Known Activations