© 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. 682
    Prev
    Next
    INDEX
    Explanations

    titles and collections

    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
     corretamente
    0.51
    ován
    0.51
    ęcia
    0.50
    desIP
    0.50
    avoro
    0.50
    ॉर्डिंग
    0.49
    ządu
    0.49
     correttamente
    0.48
    Chois
    0.47
    唕
    0.47
    POSITIVE LOGITS
     world
    0.61
     book
    0.58
     Case
    0.58
     Difference
    0.58
     difference
    0.57
     comple
    0.56
     importance
    0.56
     Evolution
    0.56
     evolution
    0.55
     reader
    0.55
    Activations Density 0.037%

    No Known Activations